build: Installed ast_grep in the sandbox kit definition

Implement support for skills and refactored secrets providers

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -21,25 +21,25 @@ body:
       value: |
         I tried this:
 
-        1. `loki`
+        1. `coyote`
 
         I expected this to happen:
 
         Instead, this happened:
   - type: textarea
-    id: loki-log
+    id: coyote-log
     attributes:
-      label: Loki log
+      label: Coyote log
-      description: Include the Loki log file to help diagnose the issue. (`loki --info` to see the log_path)
+      description: Include the Coyote log file to help diagnose the issue. (`coyote --info` to see the log_path)
       value: |
         | OS      | Log file location                                     |
         | ------- | ----------------------------------------------------- |
-        | Linux   | `~/.cache/loki/loki.log`                      |
+        | Linux   | `~/.cache/coyote/coyote.log`                      |
-        | Mac     | `~/Library/Logs/loki/loki.log`                |
+        | Mac     | `~/Library/Logs/coyote/coyote.log`                |
-        | Windows | `C:\Users\<User>\AppData\Local\loki\loki.log` |
+        | Windows | `C:\Users\<User>\AppData\Local\coyote\coyote.log` |
 
         ```
-        please provide a copy of your loki log file here if possible; you may need to redact some of the lines
+        please provide a copy of your coyote log file here if possible; you may need to redact some of the lines
         ```
 
   - type: input
@@ -57,13 +57,13 @@ body:
     validations:
       required: true
   - type: input
-    id: loki-version
+    id: coyote-version
     attributes:
-      label: Loki Version
+      label: Coyote Version
       description: >
-        Loki version (`loki --version` if using a release, `git describe` if building
+        Coyote version (`coyote --version` if using a release, `git describe` if building
         from main).
-        **Make sure that you are using the [latest loki release](https://github.com/Dark-Alex-17/loki/releases) or a newer main build**
+        **Make sure that you are using the [latest coyote release](https://github.com/Dark-Alex-17/coyote/releases) or a newer main build**
-      placeholder: "loki 0.1.0"
+      placeholder: "coyote 0.1.0"
     validations:
       required: true

.github/workflows/release.yaml

@@ -98,9 +98,9 @@ jobs:
           # Ignore Act's local artifact dir noise
           echo artifacts/ >> .git/info/exclude || true
 
-          # Edit the version line right after name="loki"
+          # Edit the version line right after name="coyote"
           sed -E -i '
-            /^[[:space:]]*name[[:space:]]*=[[:space:]]*"loki"[[:space:]]*$/ {
+            /^[[:space:]]*name[[:space:]]*=[[:space:]]*"coyote"[[:space:]]*$/ {
               n
               s|^[[:space:]]*version[[:space:]]*=[[:space:]]*"[^"]*"|version = "'"$VERSION"'"|
             }
@@ -278,7 +278,7 @@ jobs:
       - name: Verify file
         shell: bash
         run: |
-          file target/${{ matrix.target }}/release/loki
+          file target/${{ matrix.target }}/release/coyote
 
       - name: Test
         if: matrix.target != 'aarch64-apple-darwin' && matrix.target != 'aarch64-pc-windows-msvc'
@@ -382,11 +382,11 @@ jobs:
         shell: bash
         run: |
           # Set environment variables
-          macos_sha="$(cat ./artifacts/loki-x86_64-apple-darwin.sha256 | awk '{print $1}')"
+          macos_sha="$(cat ./artifacts/coyote-x86_64-apple-darwin.sha256 | awk '{print $1}')"
           echo "MACOS_SHA=$macos_sha" >> $GITHUB_ENV
-          macos_sha_arm="$(cat ./artifacts/loki-aarch64-apple-darwin.sha256 | awk '{print $1}')"
+          macos_sha_arm="$(cat ./artifacts/coyote-aarch64-apple-darwin.sha256 | awk '{print $1}')"
           echo "MACOS_SHA_ARM=$macos_sha_arm" >> $GITHUB_ENV
-          linux_sha="$(cat ./artifacts/loki-x86_64-unknown-linux-musl.sha256 | awk '{print $1}')"
+          linux_sha="$(cat ./artifacts/coyote-x86_64-unknown-linux-musl.sha256 | awk '{print $1}')"
           echo "LINUX_SHA=$linux_sha" >> $GITHUB_ENV
           release_version="$(cat ./artifacts/release-version)"
           echo "RELEASE_VERSION=$release_version" >> $GITHUB_ENV
@@ -402,23 +402,23 @@ jobs:
         if: env.ACT != 'true'
         run: |
           # run packaging script
-          python "./deployment/homebrew/packager.py" ${{ env.RELEASE_VERSION }} "./deployment/homebrew/loki.rb.template" "./loki.rb" ${{ env.MACOS_SHA }} ${{ env.MACOS_SHA_ARM }} ${{ env.LINUX_SHA }}
+          python "./deployment/homebrew/packager.py" ${{ env.RELEASE_VERSION }} "./deployment/homebrew/coyote.rb.template" "./coyote.rb" ${{ env.MACOS_SHA }} ${{ env.MACOS_SHA_ARM }} ${{ env.LINUX_SHA }}
 
       - name: Push changes to Homebrew tap
         if: env.ACT != 'true'
         env:
-          TOKEN: ${{ secrets.LOKI_GITHUB_TOKEN }}
+          TOKEN: ${{ secrets.COYOTE_GITHUB_TOKEN }}
         run: |
           # push to Git
           git config --global user.name "Dark-Alex-17"
           git config --global user.email "alex.j.tusa@gmail.com"
-          git clone https://Dark-Alex-17:${{ secrets.LOKI_GITHUB_TOKEN }}@github.com/Dark-Alex-17/homebrew-loki.git
+          git clone https://Dark-Alex-17:${{ secrets.COYOTE_GITHUB_TOKEN }}@github.com/Dark-Alex-17/homebrew-coyote.git
-          rm homebrew-loki/Formula/loki.rb
+          rm homebrew-coyote/Formula/coyote.rb
-          cp loki.rb homebrew-loki/Formula
+          cp coyote.rb homebrew-coyote/Formula
-          cd homebrew-loki
+          cd homebrew-coyote
           git add .
-          git diff-index --quiet HEAD || git commit -am "Update formula for Loki release ${{ env.RELEASE_VERSION }}"
+          git diff-index --quiet HEAD || git commit -am "Update formula for Coyote release ${{ env.RELEASE_VERSION }}"
-          git push https://$TOKEN@github.com/Dark-Alex-17/homebrew-loki.git
+          git push https://$TOKEN@github.com/Dark-Alex-17/homebrew-coyote.git
 
   publish-crate:
     needs: publish-github-release

.gitignore

@@ -3,5 +3,5 @@
 /.env
 !cli/**
 .idea/
-/loki.iml
+/coyote.iml
 /.idea/

.loki-project.json

@@ -1 +0,0 @@
-{"type":"rust","build":"cargo build","test":"cargo test","check":"cargo check","_detected_by":"heuristic","_cached_at":"2026-04-13T13:36:33-06:00"}

CHANGELOG.md

@@ -1,3 +1,274 @@
+## v0.7.4 (2026-07-02)
+
+### Feat
+
+- Pin specific usql version to sbx kit
+- recursively take ownership over the copied in coyote config for the sbx
+- explicitly specify the COYOTE_CONFIG_DIR in the sbx kit
+- --tail-logs can track log rollovers and incoporates a sleep timer to minimize idle CPU cycles
+- Added support for log rolling so log files don't just blow up over time
+
+### Fix
+
+- Added back in --kit specification for the running of the sbx
+- sbx isn't copying base files in their respective directories
+- Update deprecated sbx kit config
+- Properly chown the coyote config recursively and password file in the sbx
+
+## v0.7.3 (2026-06-24)
+
+### Fix
+
+- apply bootstrapping of functions at startup to fix edge case
+
+## v0.7.2 (2026-06-19)
+
+### Fix
+
+- usql version upgrade
+
+## v0.7.1 (2026-06-19)
+
+### Fix
+
+- sbx mixins must be passed in directories, not as files and the files must be named spec.yaml per new sbx version
+
+## v0.7.0 (2026-06-18)
+
+### Feat
+
+- added configurable cache path via the COYOTE_CACHE_PATH environment variable
+- added a memory option to .set tab completions
+- Added a diagnostic .info tools subcommand to make it easier to see what tools are enabled in all contexts
+- Added additional info outputs for enabled skills and sbx directories
+- directly execute shell commands from within the REPL
+- created mixin kit for built-in functions and MCP servers
+- Added sbx mixins for the secrets providers so users can also bootstrap those as well.
+- added support for loading sbx mixins that are dynamically discovered in the users workspace and config directory
+- Added a --fresh flag to let users create a truly bare bones sandbox without bootstrapping their config
+- initial built-in sandboxing support powered by Docker sbx
+- Added the ability to auto-bootstrap workspace memory when in git repos
+- Added explicit guardrail handling for pending agents
+- auto-append memory to memory index and don't necessarily require the LLM to remember to do it after a write
+- Added an --init-memory [global|workspace] flag to easily and quickly enable memory
+- added memory global configuration settings to the output of --info and .info
+- added .set memory REPL commands to control memory injection and applied formatting
+- Create the built-in memory management tools
+- Append the memory system prompts (readonly or r/w) to the system prompt when applicable
+- Created the --no-memory CLI flag to disable memory for this invocation
+- Added the memory configuration properties and storage to the main app config, roles, sessions, and agents.
+- initial scaffolding of a memory system
+
+### Fix
+
+- rebuild the tool scope after dynamically updating the skills_enabled value in the REPL
+- properly resolve Windows-based local vault password file locations and bootstrap them into the sandbox when possible
+- auto-translation of user-prefixed Mac and Linux paths for the vault password file when running inside a sandbox
+- don't attempt to auto complete .vault list in the REPL; that's the end of the command
+- buffer tool stdout as well as stderr so that any tools that error to stdout are captured and included in the response to the model, enabling the model to see what went wrong and to reason about how to fix it.
+- auto-bootstrapped memory was accidentally putting the MEMORY.md directly in the repo root rather than .coyote/memory/MEMORY.md
+- improved the fs_patch script description and added improved error handling to it.
+- added in forgotten require_max_tokens to the fable model
+- append memory functions to non-graph based agents on init
+- when auto_continue is disabled via the .set auto_continue false command, it should strip the todo functions from the list of functions
+- use rawPredict for non-streaming Claude requests
+
+### Refactor
+
+- Migrated the .skills command completion to use StateFlags and updated the help messages
+
+## v0.6.0 (2026-06-05)
+
+### Feat
+
+- added skill hint prompt injection and configuration
+- Fallthrough on missing secrets during mcp.json merging
+- validate visible_skills field at config load time
+- implemented reflexion (sorta) in sisyphus for significant code changes to delegate to the code-reviewer agent
+- improved explore agent
+- removed conditional fallback of LLM_*_RAW_JSON from built-ins
+- updated enabled_skills handling to support both list and comma-separated strings
+- added new REPL set commands for toggling skills and changing what skills are enabled
+- upgraded to the latest version of mcp-remote
+- fs_grep now works with both files and directories
+- improved code reviewer agents with skills
+- added round trip validation for vault providers to ensure permissions and authentication
+- created new first-time run wizard for secrets provider
+- vault_password_file or nothing at all is shorthand for just using the local gman provider for secret management
+- refactored gman usage to be generic and work with various vault providers and use the SupportedProvider enum directly for configurations
+- created initial parity gman generalization for vault provider
+- Refactored the sisyhpus agent system to utilize the new skills system to improve performance and reliability
+- llm graph nodes support skills
+- updated sisyphus and coder tools
+- removed potentially confusing tab completions for .skill
+- .edit skill <name> support from within the REPL
+- Added skills_dir to the info output of Coyote
+- Created a few auto built-in skills
+- Added support for auto_unload skills during chat
+- cleaned up skill implementation
+- support multiple skill flags to load multiple skills at CLI startup
+- Modified --skill CLI to allow users to specify skills to start the REPL or CLI with.
+- added CLI --skill flag for modifying skills easily
+- REPL integration with skills
+- dynamic loading/unloading of skill tools and MCP servers whenever load_skill/unload_skill are invoked
+- created built-in functions for listing, loading, and unloading skills
+- implemented the skills policy to track available skills per context
+- added remote install and install support for skills
+- created the skill registry
+- decided to make skills persist to disk like agents and not in-memory like built-in roles
+- scaffold skill module
+
+### Fix
+
+- disable skills for specific built-in roles
+- redirect stderr into user's /dev/tty for guards
+- azure doesn't support underscores in key vault
+- accidental regression on enabled_skills being empty = all
+- greedy secrets regex caused multiple secrets on one line to fail
+- add agent context check to skill visibility validation
+- enforced global visible_skills in llm node validation and improved skill loading error handling across the project
+- restore agent skill policy on error during effective policy calculation
+- apply the same validation for skill filenames on list_skills as happens everywhere else
+- the vault's init_bare should try to load the provisioned secret_provider from the config file without also interpolating any of the rest of the configuration file. It should only fail if the user has not yet created a configuration file; i.e. done a first-time run.
+- the vault roundtrip test used characters that are unsupported by some major secrets providers
+- fixed tool filtering logic for skills and user functions in agents
+- privilege leak when unloading skills and leaving tool scope untouched
+- When bootstrapping an app config to interpolate secrets, clone the secrets provider configuration as well so config secrets stored in remote vaults can be used properly
+- forgot to move back up the vault probe value error to be before the delete
+- don't silently fail on skill role composition extraction in llm nodes
+- set -euo pipefail for the temp script in execute_command.sh tool
+- added forgotten skill name validation to has_skill to prevent side-channel attacks
+- use unique values for the secrets round trip verification
+- stop interpolating a line if any errors occur
+- added path validation for skill names
+- effective_policy unconditionally overwrote skill values for role-like structs
+- updated execute_command to not mangle heredocs and also added explicit instructions to the coder and sisyphus agents to use fs_write and fs_patch over execute_command when writing files
+- llm nodes accidentally skipped skill_registry::effective_role because I was passing an inline role instead
+- updated temperature values for all agents and roles
+- added back in require_max_tokens for new Claude models
+- skill support also requires function calling to be enabled
+- non_tty tests break on some TTY terminals
+- skill loading on agents
+- forgot to bootstrap skills on REPL startup
+- remove now deprecated .skill edit command
+
+### Refactor
+
+- removed redundant skill name validation from has_skill function
+- support both CSV and list formats for enabled_tools
+- Support both CSV and list formats for enabled_mcp_servers
+
+## v0.5.0 (2026-05-27)
+
+### Feat
+
+- rename Loki to Coyote
+
+### Fix
+
+- bash-based user interactions in agents accidentally regressed in graph implementation
+- Claude function calling in agent contexts
+- Claude code rate limit error per new Claude changes
+
+## v0.4.0 (2026-05-23)
+
+### Feat
+
+- LLM node failures propgate up
+- Added .install remote tab completions to the REPL
+- feature complete install remote with category selection
+- Support to interactively add secrets to Coyote that are missing from MCP configs when merging
+- Added MCP config merging support for remote asset installations
+- install remote now writes files to disk
+- Created basic install_remote functions
+- Created a more comprehensive and immediately useful default config for first runs
+- Created an example graph-based agent called deep-research
+- Improved coder agent that is now a graph-based agent
+- Removed indicatif spinners. The UX just won't stop clobbering for parallel graph nodes
+- Added agent variables support for graph agents and improved script executor to use the same environment variables as normal agent tool calling for further flexibility
+- Improved UX with colored spinners for parallel graph agents and no clobbering outputs for sub-agents
+- created new graph-based deep-research agent
+- improved UX for parallel graph execution
+- added branch progress tracker for better visualization of parallel graph super-steps
+- Removed the jira-helper agent and replaced it with the atlassian role
+- created the RenderMode enum to suppress stdout streaming during parallel graph super-steps
+- Full support for map node types
+- implemented the frontier-based scheduling for the graph executor with simplified state management (gotta love .clone)
+- validation support for parallel graph execution; restricted map nodes to only run for nodes without next targets and not supporting chained map nodes
+- created the staging area for state merges per super-step and created the built-in reducers (and their application) for the state merge phase of a super step
+- scaffolding work for fan-out nodes for parallel branch execution support and stubbed out Map node types
+- Coyote can now update itself via .update and --update commands
+- added a .edit command for editing the MCP configuration file
+- Created a new .install command to install bundled assets on-demand
+- migrated llm node validation to graph loading time instead of graph runtime
+- ripped out user input timeout scaffolding for approval and input node types; implementation can't be done cleanly
+- added additional support for all RAG-configuration fields in RAG nodes
+- initial support for RAG nodes in the graph execution system
+- implemented structured logging for graph execution
+- merged normal agent config and graph agent configs into one file (either/or)
+- added structured-output extraction for llm and agent nodes
+- created full llm node runtime implementation
+- scaffolded together the initial llm node type and its executor
+- wired together graph execution and agent graph dispatch
+- implemented support for the graph executor
+- created the approval node executor and the input node executor for user interaction
+- Added initial support for native Coyote agent nodes in the graph-based agent system
+- Added direct script invocation support for graph-based agents
+- Added graph validation
+- Implemented state management for agent graphs
+- initial agent graph scaffolding
+- add auto-continue support to all contexts
+- dynamic tab completions now show the sessions for a given agent instead of only listing global sessions
+- legacy SSE support for MCP server configurations
+- support http/sse transport types for MCP server configurations so it fully supports claude desktop-style MCP configs
+- 99% complete migration to new state structs to get away from God-Config struct; i.e. AppConfig, AppState, and RequestContext
+- Automatic runtime customization using shebangs
+- Created a demo TypeScript tool and a get_current_weather function in TypeScript
+- Updated the Python demo tool to show all possible parameter types and variations
+- Added TypeScript tool support using the refactored common ScriptedLanguage trait
+
+### Fix
+
+- Generified the functions usage of script detection for an executable bit on unix systems
+- merge required claude code system prompt into instructions
+- updated argc argument passing in run-tool and run-agent scripts
+- Added additional graph validation for parallel reads and writes with dependencies between nodes states
+- bug in next_single method and improved outcome handling for LLM node execution
+- inline RAG bug when globbing files by extension without subdirectory globbing
+- update the estimate_token_length function to use the standard word count method
+- removed unnecessary regenerate logic for sessions and use the same logic for all contexts; prevents a panic on empty message list
+- error when users try to start a session on a graph agent
+- added on_other field for approval nodes so users can specify an alternative free-text target when none of the options match what they want
+- accidentally added back in full agent tools on LLM nodes
+- Improve the coder agent's usage of tools
+- make the agent__collect escalation-aware so it doesn't freeze on sub-agent escalations
+- check for an existing session before starting up MCP servers when switching to a role
+- do not switch to agent if a session is active.
+- Do not append todo instructions when function calling is disabled
+- a bug in the dynamic completions because the crate name is coyote-ai but the binary is named coyote
+- bug found by copilot that would create a lock on the PollSender for sse-based MCP servers
+- Accidental shadow of temp_file function for Windows function calling
+- upgraded to newer rmcp version to get native-tls support
+- RagCache was not being used for agent and sub-agent instantiation
+- TypeScript function args were being passed as objects rather than direct parameters
+- Added in forgotten wrapper scripts for TypeScript tools
+- don't shadow variables in binary path handling for Windows
+- Tool call improvements for Windows systems
+
+### Refactor
+
+- migrated llm nodes to use Roles to simplify instructions handling and to function like inline roles
+- migrated the next_node and apply_state_updates logic for LLM nodes into the LlmExecutor
+- fully complete state re-architecting
+- Fully ripped out the god Config struct
+- Deprecated old Config struct initialization logic
+- migrate functions and MCP servers to AppConfig
+- Migrate the vault/bare_init logic
+- created a single install_builtins free function to remove from Config::init
+- partial migration to init in AppConfig
+- Extracted common Python parser logic into a common.rs module
+- python tools now use tree-sitter queries instead of AST
+
 ## v0.3.0 (2026-04-02)
 
 ### Feat
@@ -21,7 +292,7 @@
 - Created a CodeRabbit-style code-reviewer agent
 - Added configuration option in agents to indicate the timeout for user input before proceeding (defaults to 5 minutes)
 - Added support for sub-agents to escalate user interaction requests from any depth to the parent agents for user interactions
-- built-in user interaction tools to remove the need for the list/confirm/etc prompts in prompt tools and to enhance user interactions in Loki
+- built-in user interaction tools to remove the need for the list/confirm/etc prompts in prompt tools and to enhance user interactions in Coyote
 - Experimental update to sisyphus to use the new parallel agent spawning system
 - Added an agent configuration property that allows auto-injecting sub-agent spawning instructions (when using the built-in sub-agent spawning system)
 - Auto-dispatch support of sub-agents and support for the teammate pattern between subagents
@@ -75,7 +346,7 @@
 
 - Simplified sisyphus prompt to improve functionality
 - Supported the injection of RAG sources into the prompt, not just via the `.sources rag` command in the REPL so models can directly reference the documents that supported their responses
-- Created the Sisyphus agent to make Loki function like Claude Code, Gemini, Codex, etc.
+- Created the Sisyphus agent to make Coyote function like Claude Code, Gemini, Codex, etc.
 - Created the Oracle agent to handle high-level architectural decisions and design questions about a given codebase
 - Updated the coder agent to be much more task-focused and to be delegated to by Sisyphus
 - Created the explore agent for exploring codebases to help answer questions
@@ -135,8 +406,8 @@
 - Support for secret injection into the global config file (API keys, for example)
 - Improved MCP handling toggle handling
 - Secret injection into the MCP configuration
-- added REPL support for interacting with the Loki vault
+- added REPL support for interacting with the Coyote vault
-- Integrated gman with Loki to create a vault and added flags to configure the Loki vault
+- Integrated gman with Coyote to create a vault and added flags to configure the Coyote vault
 - Added a default session to the jira helper to make interaction more natural
 - Created the repo-analyzer role
 - Created the coder and sql agents

CONTRIBUTING.md

@@ -2,7 +2,7 @@
 Contributors are very welcome! **No contribution is too small and all contributions are valued.**
 
 ## Rust
-You'll need to have the stable Rust toolchain installed in order to develop Loki.
+You'll need to have the stable Rust toolchain installed in order to develop Coyote.
 
 The Rust toolchain (stable) can be installed via rustup using the following command:
 
@@ -84,5 +84,5 @@ Claude, etc.) is not permitted unless explicitly disclosed and approved.
 Submissions must certify that the contributor understands and can maintain the code they submit.
 
 ## Questions? Reach out to me!
-If you encounter any questions while developing Loki, please don't hesitate to reach out to me at 
+If you encounter any questions while developing Coyote, please don't hesitate to reach out to me at 
 alex.j.tusa@gmail.com. I'm happy to help contributors in any way I can, regardless of if they're new or experienced!

CREDITS.md

@@ -1,19 +1,19 @@
 # Credits
 
 ## AIChat
-Loki originally started as a fork of the fantastic
+Coyote originally started as a fork of the fantastic
 [AIChat CLI](https://github.com/sigoden/aichat). The initial goal was simply
 to fix a bug in how MCP servers worked with AIChat, allowing different MCP
-servers to be specified per agent. Since then, Loki has evolved far beyond
+servers to be specified per agent. Since then, Coyote has evolved far beyond
 its original scope and grown into a passion project with a life of its own.
 
-Today, Loki includes first-class MCP server support (for both local and remote
+Today, Coyote includes first-class MCP server support (for both local and remote
 servers), a built-in vault for interpolating secrets in configuration files,
 built-in agents and macros, dynamic tab completions, integrated custom
 functions (no external `argc` dependency), improved documentation, and much
 more with many more ideas planned for the future.
 
-Loki is now developed and maintained as an independent project. Full credit
+Coyote is now developed and maintained as an independent project. Full credit
 for the original foundation goes to the developers of the wonderful
 AIChat project.
 
@@ -21,10 +21,10 @@ This project is not affiliated with or endorsed by the AIChat maintainers.
 
 ## AIChat
 
-Loki originally began as a fork of [AIChat CLI](https://github.com/sigoden/aichat),
+Coyote originally began as a fork of [AIChat CLI](https://github.com/sigoden/aichat),
 created and maintained by the AIChat contributors.
 
-While Loki has since diverged significantly and is now developed as an
+While Coyote has since diverged significantly and is now developed as an
 independent project, its early foundation and inspiration came from the
 AIChat project.
 

Cargo.toml

@@ -1,16 +1,16 @@
 [package]
-name = "loki-ai"
+name = "coyote-ai"
-version = "0.3.0"
+version = "0.7.4"
 edition = "2024"
 authors = ["Alex Clarke <alex.j.tusa@gmail.com>"]
 description = "An all-in-one, batteries included LLM CLI Tool"
 keywords = ["chatgpt", "llm", "cli", "ai", "repl"]
-homepage = "https://github.com/Dark-Alex-17/loki"
+homepage = "https://github.com/Dark-Alex-17/coyote"
-repository = "https://github.com/Dark-Alex-17/loki"
+repository = "https://github.com/Dark-Alex-17/coyote"
 categories = ["command-line-utilities"]
 readme = "README.md"
 license = "MIT"
-rust-version = "1.89.0"
+rust-version = "1.95.0"
 exclude = [".github", "CONTRIBUTING.md"]
 
 [dependencies]
@@ -49,7 +49,7 @@ textwrap = "0.16.0"
 ansi_colours = "1.2.2"
 eventsource-stream = "0.2.3"
 log = "0.4.28"
-log4rs = { version = "1.4.0", features = ["file_appender"] }
+log4rs = { version = "1.4.0", features = ["file_appender", "rolling_file_appender", "compound_policy", "fixed_window_roller", "size_trigger"] }
 shell-words = "1.1.0"
 sha2 = "0.10.8"
 unicode-width = "0.2.0"
@@ -58,6 +58,8 @@ http = "1.1.0"
 indexmap = { version = "2.2.6", features = ["serde"] }
 hmac = "0.12.1"
 aws-smithy-eventstream = "0.60.4"
+aws-smithy-types = "=1.4.9"
+time = "=0.3.47"
 urlencoding = "2.1.3"
 json-patch = { version = "4.0.0", default-features = false }
 bitflags = "2.5.0"
@@ -91,7 +93,7 @@ tree-sitter-python = "0.25.0"
 tree-sitter-typescript = "0.23"
 colored = "3.0.0"
 clap_complete = { version = "4.5.58", features = ["unstable-dynamic"] }
-gman = "0.4.1"
+gman = "0.5.0"
 clap_complete_nushell = "4.5.9"
 open = "5"
 rand = { version = "0.10.0", features = ["default"] }
@@ -138,7 +140,7 @@ pretty_assertions = "1.4.0"
 serial_test = "3"
 
 [[bin]]
-name = "loki"
+name = "coyote"
 path = "src/main.rs"
 
 [profile.release]

README.md

@@ -1,54 +1,57 @@
-# Loki: All-in-one, batteries-included LLM CLI Tool
+# Coyote: All-in-one, batteries-included LLM CLI Tool
 
-![Test](https://github.com/Dark-Alex-17/loki/actions/workflows/ci.yaml/badge.svg)
+![Test](https://github.com/Dark-Alex-17/coyote/actions/workflows/ci.yaml/badge.svg)
-[![crates.io link](https://img.shields.io/crates/v/loki-ai.svg)](https://crates.io/crates/loki-ai)
+[![crates.io link](https://img.shields.io/crates/v/coyote-ai.svg)](https://crates.io/crates/coyote-ai)
-![Release](https://img.shields.io/github/v/release/Dark-Alex-17/loki?color=%23c694ff)
+![Release](https://img.shields.io/github/v/release/Dark-Alex-17/coyote?color=%23c694ff)
-![Crate.io downloads](https://img.shields.io/crates/d/loki-ai?label=Crate%20downloads)
+![Crate.io downloads](https://img.shields.io/crates/d/coyote-ai?label=Crate%20downloads)
-[![GitHub Downloads](https://img.shields.io/github/downloads/Dark-Alex-17/loki/total.svg?label=GitHub%20downloads)](https://github.com/Dark-Alex-17/loki/releases)
+[![GitHub Downloads](https://img.shields.io/github/downloads/Dark-Alex-17/coyote/total.svg?label=GitHub%20downloads)](https://github.com/Dark-Alex-17/coyote/releases)
 
-Loki is an all-in-one, batteries-included, LLM CLI tool featuring Shell Assistant, CLI & REPL Mode, RAG, AI Tools & 
+Coyote is an all-in-one, batteries-included, LLM CLI tool featuring Shell Assistant, CLI & REPL Mode, RAG, AI Tools & 
 Agents, and More.
 
-It is designed to include a number of useful agents, roles, macros, and more so users can get up and running with Loki 
+It is designed to include a number of useful agents, roles, macros, and more so users can get up and running with Coyote 
 in as little time as possible. You can also install entire bundles of agents, roles, macros, tools, and MCP servers from 
-any git repository — see [Sharing Configurations](#sharing-configurations).
+any git repository. See [Sharing Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Sharing-Configurations) for more information.
 
-![Agent example](https://raw.githubusercontent.com/wiki/Dark-Alex-17/loki/images/agents/sql.gif)
+![Agent example](https://raw.githubusercontent.com/wiki/Dark-Alex-17/coyote/images/agents/sql.gif)
 
-Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration guide](https://github.com/Dark-Alex-17/loki/wiki/AIChat-Migration) to get started.
+Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration guide](https://github.com/Dark-Alex-17/coyote/wiki/AIChat-Migration) to get started.
 
 ## Quick Links
-* [AIChat Migration Guide](https://github.com/Dark-Alex-17/loki/wiki/AIChat-Migration): Coming from AIChat? Follow the migration guide to get started.
+* [AIChat Migration Guide](https://github.com/Dark-Alex-17/coyote/wiki/AIChat-Migration): Coming from AIChat? Follow the migration guide to get started.
-* [Installation](#install): Install Loki
+* [Installation](#install): Install Coyote
-* [Getting Started](#getting-started): Get started with Loki by doing first-run setup steps.
+* [Getting Started](#getting-started): Get started with Coyote by doing first-run setup steps.
-* [Sharing Configurations](https://github.com/Dark-Alex-17/loki/wiki/Sharing-Configurations): Install bundles of agents, roles, macros, tools, and MCP servers from any git repo, and share your own.
+* [Sharing Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Sharing-Configurations): Install bundles of agents, roles, macros, tools, and MCP servers from any git repo, and share your own.
-* [REPL](https://github.com/Dark-Alex-17/loki/wiki/REPL): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Loki.
+* [REPL](https://github.com/Dark-Alex-17/coyote/wiki/REPL): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Coyote.
-  * [Custom REPL Prompt](https://github.com/Dark-Alex-17/loki/wiki/REPL-Prompt): Customize the REPL prompt to provide useful contextual information.
+  * [Custom REPL Prompt](https://github.com/Dark-Alex-17/coyote/wiki/REPL-Prompt): Customize the REPL prompt to provide useful contextual information.
-* [Vault](https://github.com/Dark-Alex-17/loki/wiki/Vault): Securely store and manage sensitive information such as API keys and credentials.
+* [Vault](https://github.com/Dark-Alex-17/coyote/wiki/Vault): Securely store and manage sensitive information such as API keys and credentials.
-* [Shell Integrations](https://github.com/Dark-Alex-17/loki/wiki/Shell-Integrations): Seamlessly integrate Loki with your shell environment for enhanced command-line assistance.
+* [Sandboxes](https://github.com/Dark-Alex-17/coyote/wiki/Sandboxes): Launch Coyote inside an isolated [Docker Sandbox](https://docs.docker.com/ai/sandboxes/) with one command. Host config and vault credentials are projected in automatically; everything else is delegated to the `sbx` CLI.
-* [Function Calling](https://github.com/Dark-Alex-17/loki/wiki/Tools): Leverage function calling capabilities to extend Loki's functionality with custom tools
+* [Shell Integrations](https://github.com/Dark-Alex-17/coyote/wiki/Shell-Integrations): Seamlessly integrate Coyote with your shell environment for enhanced command-line assistance.
-    * [Creating Custom Tools](https://github.com/Dark-Alex-17/loki/wiki/Custom-Tools): You can create your own custom tools to enhance Loki's capabilities.
+* [Function Calling](https://github.com/Dark-Alex-17/coyote/wiki/Tools): Leverage function calling capabilities to extend Coyote's functionality with custom tools
-        * [Create Custom Python Tools](https://github.com/Dark-Alex-17/loki/wiki/Custom-Tools#custom-python-based-tools)
+    * [Creating Custom Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools): You can create your own custom tools to enhance Coyote's capabilities.
-        * [Create Custom TypeScript Tools](https://github.com/Dark-Alex-17/loki/wiki/Custom-Tools#custom-typescript-based-tools)
+        * [Create Custom Python Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-python-based-tools)
-        * [Create Custom Bash Tools](https://github.com/Dark-Alex-17/loki/wiki/Custom-Bash-Tools)
+        * [Create Custom TypeScript Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-typescript-based-tools)
-            * [Bash Prompt Utilities](https://github.com/Dark-Alex-17/loki/wiki/Bash-Prompt-Helpers)
+        * [Create Custom Bash Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Bash-Tools)
-* [First-Class MCP Server Support](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers): Easily connect and interact with MCP servers for advanced functionality.
+            * [Bash Prompt Utilities](https://github.com/Dark-Alex-17/coyote/wiki/Bash-Prompt-Helpers)
-* [Macros](https://github.com/Dark-Alex-17/loki/wiki/Macros): Automate repetitive tasks and workflows with Loki "scripts" (macros).
+* [First-Class MCP Server Support](https://github.com/Dark-Alex-17/coyote/wiki/MCP-Servers): Easily connect and interact with MCP servers for advanced functionality.
-* [RAG](https://github.com/Dark-Alex-17/loki/wiki/RAG): Retrieval-Augmented Generation for enhanced information retrieval and generation.
+* [Macros](https://github.com/Dark-Alex-17/coyote/wiki/Macros): Automate repetitive tasks and workflows with Coyote "scripts" (macros).
-* [Sessions](https://github.com/Dark-Alex-17/loki/wiki/Sessions): Manage and persist conversational contexts and settings across multiple interactions.
+* [RAG](https://github.com/Dark-Alex-17/coyote/wiki/RAG): Retrieval-Augmented Generation for enhanced information retrieval and generation.
-* [Roles](https://github.com/Dark-Alex-17/loki/wiki/Roles): Customize model behavior for specific tasks or domains.
+* [Sessions](https://github.com/Dark-Alex-17/coyote/wiki/Sessions): Manage and persist conversational contexts and settings across multiple interactions.
-* [Agents](https://github.com/Dark-Alex-17/loki/wiki/Agents): Leverage AI agents to perform complex tasks and workflows, including sub-agent spawning, teammate messaging, and user interaction tools.
+* [Memory](https://github.com/Dark-Alex-17/coyote/wiki/Memory): Persistent file-based memory that survives across sessions. Bootstrap with `coyote --init-memory [global|workspace]`.
-    * [Graph Agents](https://github.com/Dark-Alex-17/loki/wiki/Graph-Agents): Define an agent as a declarative, YAML-driven workflow. A directed graph of typed nodes (LLM calls, scripts, approvals, user input, RAG retrieval, sub-agent spawns).
+* [Roles](https://github.com/Dark-Alex-17/coyote/wiki/Roles): Customize model behavior for specific tasks or domains.
-* [Todo System](https://github.com/Dark-Alex-17/loki/wiki/TODO-System): Built-in task tracking for improved LLM reliability with smaller models.
+* [Skills](https://github.com/Dark-Alex-17/coyote/wiki/Skills): Modular knowledge or capability packs the LLM can load and unload mid-conversation. Multiple skills compose; instructions stack, tools and MCPs union.
-* [Environment Variables](https://github.com/Dark-Alex-17/loki/wiki/Environment-Variables): Override and customize your Loki configuration at runtime with environment variables.
+* [Agents](https://github.com/Dark-Alex-17/coyote/wiki/Agents): Leverage AI agents to perform complex tasks and workflows, including sub-agent spawning, teammate messaging, and user interaction tools.
-* [Client Configurations](https://github.com/Dark-Alex-17/loki/wiki/Clients): Configuration instructions for various LLM providers.
+    * [Graph Agents](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents): Define an agent as a declarative, YAML-driven workflow. A directed graph of typed nodes (LLM calls, scripts, approvals, user input, RAG retrieval, sub-agent spawns).
-    * [Authentication (API Key & OAuth)](https://github.com/Dark-Alex-17/loki/wiki/Clients#authentication): Authenticate with API keys or OAuth for subscription-based access.
+* [Todo System](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System): Built-in task tracking for improved LLM reliability with smaller models.
-    * [Patching API Requests](https://github.com/Dark-Alex-17/loki/wiki/Patches): Learn how to patch API requests for advanced customization.
+* [Environment Variables](https://github.com/Dark-Alex-17/coyote/wiki/Environment-Variables): Override and customize your Coyote configuration at runtime with environment variables.
-* [Custom Themes](https://github.com/Dark-Alex-17/loki/wiki/Themes): Change the look and feel of Loki to your preferences with custom themes.
+* [Client Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Clients): Configuration instructions for various LLM providers.
-* [History](#history): A history of how Loki came to be.
+    * [Authentication (API Key & OAuth)](https://github.com/Dark-Alex-17/coyote/wiki/Clients#authentication): Authenticate with API keys or OAuth for subscription-based access.
+    * [Patching API Requests](https://github.com/Dark-Alex-17/coyote/wiki/Patches): Learn how to patch API requests for advanced customization.
+* [Custom Themes](https://github.com/Dark-Alex-17/coyote/wiki/Themes): Change the look and feel of Coyote to your preferences with custom themes.
+* [History](#history): A history of how Coyote came to be.
 
 ## Prerequisites
-Loki requires the following tools to be installed on your system:
+Coyote requires the following tools to be installed on your system:
 * [jq](https://github.com/jqlang/jq)
     * `brew install jq`
 * [usql](https://github.com/xo/usql) (For the `sql` agent)
@@ -56,58 +59,66 @@ Loki requires the following tools to be installed on your system:
 * [docker](https://docs.docker.com/engine/install/)
 * [uv](https://docs.astral.sh/uv/getting-started/installation/)
     * `curl -LsSf https://astral.sh/uv/install.sh | sh`
+* [iwe](https://github.com/iwe-org/iwe) (`iwec`, for the built-in `iwe` MCP server that navigates large markdown knowledgebases)
+    * **Homebrew:** `brew tap iwe-org/iwe && brew install iwe`
+    * **Cargo:** `cargo install iwec`
+* [ast-grep](https://ast-grep.github.io/) (for the built-in `ast_grep` structural code search tool, used by the `explore` agent)
+    * **Homebrew:** `brew install ast-grep`
+    * **Cargo:** `cargo install ast-grep --locked`
+    * **npm:** `npm i -g @ast-grep/cli`
+    * Optional: if `ast-grep` is not installed, the `ast_grep` tool reports it and agents fall back to `fs_grep`
 
-These tools are used to provide various functionalities within Loki, such as document processing, JSON manipulation,
+These tools are used to provide various functionalities within Coyote, such as document processing, JSON manipulation,
 etc., and they are used within agents and tools.
 
 ## Install
 
 ### Cargo
-If you have Cargo installed, then you can install `loki` from Crates.io:
+If you have Cargo installed, then you can install `coyote` from Crates.io:
 
 ```shell
-cargo install loki-ai # Binary name is `loki`
+cargo install coyote-ai # Binary name is `coyote`
 
 # If you encounter issues installing, try installing with '--locked'
-cargo install --locked loki-ai
+cargo install --locked coyote-ai
 ```
 
 ### Homebrew (Mac/Linux)
-To install Loki from Homebrew, install the `loki` tap. Then you'll be able to install `loki`:
+To install Coyote from Homebrew, install the `coyote` tap. Then you'll be able to install `coyote`:
 
 ```shell
-brew tap Dark-Alex-17/loki
+brew tap Dark-Alex-17/coyote
-brew install loki
+brew install coyote
 
 # If you need to be more specific, use:
-brew install Dark-Alex-17/loki/loki
+brew install Dark-Alex-17/coyote/coyote
 ```
 
-To upgrade `loki` using Homebrew:
+To upgrade `coyote` using Homebrew:
 
 ```shell
-brew upgrade loki
+brew upgrade coyote
 ```
 
 ### Scripts
 #### Linux/MacOS (`bash`)
-You can use the following command to run a bash script that downloads and installs the latest version of `loki` for your
+You can use the following command to run a bash script that downloads and installs the latest version of `coyote` for your
 OS (Linux/MacOS) and architecture (x86_64/arm64):
 
 ```shell
-curl -fsSL https://raw.githubusercontent.com/Dark-Alex-17/loki/main/install_loki.sh | bash
+curl -fsSL https://raw.githubusercontent.com/Dark-Alex-17/coyote/refs/heads/main/scripts/install_coyote.sh | bash
 ```
 
 #### Windows/Linux/MacOS (`PowerShell`)
-You can use the following command to run a PowerShell script that downloads and installs the latest version of `loki`
+You can use the following command to run a PowerShell script that downloads and installs the latest version of `coyote`
 for your OS (Windows/Linux/MacOS) and architecture (x86_64/arm64):
 
 ```powershell
-powershell -NoProfile -ExecutionPolicy Bypass -Command "iwr -useb https://raw.githubusercontent.com/Dark-Alex-17/loki/main/scripts/install_loki.ps1 | iex"
+powershell -NoProfile -ExecutionPolicy Bypass -Command "iwr -useb https://raw.githubusercontent.com/Dark-Alex-17/coyote/refs/heads/main/scripts/install_coyote.ps1 | iex"
 ```
 
 ### Manual
-Binaries are available on the [releases](https://github.com/Dark-Alex-17/loki/releases) page for the following platforms:
+Binaries are available on the [releases](https://github.com/Dark-Alex-17/coyote/releases) page for the following platforms:
 
 | Platform       | Architecture(s) |
 |----------------|-----------------|
@@ -118,102 +129,103 @@ Binaries are available on the [releases](https://github.com/Dark-Alex-17/loki/re
 #### Windows Instructions
 To use a binary from the releases page on Windows, do the following:
 
-1. Download the latest [binary](https://github.com/Dark-Alex-17/loki/releases) for your OS.
+1. Download the latest [binary](https://github.com/Dark-Alex-17/coyote/releases) for your OS.
 2. Use 7-Zip or TarTool to unpack the Tar file.
-3. Run the executable `loki.exe`!
+3. Run the executable `coyote.exe`!
 
 #### Linux/MacOS Instructions
 To use a binary from the releases page on Linux/MacOS, do the following:
 
-1. Download the latest [binary](https://github.com/Dark-Alex-17/loki/releases) for your OS.
+1. Download the latest [binary](https://github.com/Dark-Alex-17/coyote/releases) for your OS.
 2. `cd` to the directory where you downloaded the binary.
-3. Extract the binary with `tar -C /usr/local/bin -xzf loki-<arch>.tar.gz` (Note: This may require `sudo`)
+3. Extract the binary with `tar -C /usr/local/bin -xzf coyote-<arch>.tar.gz` (Note: This may require `sudo`)
-4. Now you can run `loki`!
+4. Now you can run `coyote`!
 
 ## Updating
-Loki can update itself in place to the latest GitHub release. Run `loki --update`
+Coyote can update itself in place to the latest GitHub release. Run `coyote --update`
-for the newest release, or `loki --update v0.4.0` for a specific version:
+for the newest release, or `coyote --update v0.4.0` for a specific version:
 
 ```shell
-loki --update
+coyote --update
-loki --update v0.4.0
+coyote --update v0.4.0
 ```
 
 The same is available from within the REPL via `.update` and `.update v0.4.0`.
 
-If Loki was installed with a package manager, prefer that package manager so its
+If Coyote was installed with a package manager, prefer that package manager so its
-records stay in sync with the binary on disk; i.e. `brew upgrade loki` for Homebrew,
+records stay in sync with the binary on disk; i.e. `brew upgrade coyote` for Homebrew,
-or `cargo install --locked loki-ai` for Cargo.
+or `cargo install --locked coyote-ai` for Cargo.
 
-When Loki detects a package-manager install it prints a warning and asks for
+When Coyote detects a package-manager install it prints a warning and asks for
 confirmation. In a non-interactive shell (no TTY), pass `--force` to update
 anyway:
 
 ```shell
-loki --update --force
+coyote --update --force
 ```
 
 ## Getting Started
 After installation, you can generate the configuration files and directories by simply running:
 
 ```sh
-loki --info
+coyote --info
 ```
 
-Then, you need to set up the Loki vault by creating a vault password file. Loki will do this for you automatically and
+Then, you need to set up the Coyote vault by creating a vault password file. Coyote will do this for you automatically and
 guide you through the process when you first attempt to access the vault. So, to get started, you can run:
 
 ```sh
-loki --list-secrets
+coyote --list-secrets
 ```
 
 ### Authentication
 Each client in your configuration needs authentication (with a few exceptions; e.g. ollama). Most clients use an API key
-(set via `api_key` in the config or through the [vault](https://github.com/Dark-Alex-17/loki/wiki/Vault)). For providers that support OAuth (e.g. Claude Pro/Max 
+(set via `api_key` in the config or through the [vault](https://github.com/Dark-Alex-17/coyote/wiki/Vault)). For providers that support OAuth (e.g. Claude Pro/Max 
 subscribers, Google Gemini), you can authenticate with your existing subscription instead:
 
 ```yaml
 # In your config.yaml
 clients:
   - type: claude
+    name: my-claude-oauth
     auth: oauth # Indicate you want to authenticate with OAuth instead of an API key
 ```
 
 ```sh
-loki --authenticate claude
+coyote --authenticate my-claude-oauth
 # Or via the REPL: .authenticate
 ```
 
-For full details, see the [authentication documentation](https://github.com/Dark-Alex-17/loki/wiki/Clients#authentication).
+For full details, see the [authentication documentation](https://github.com/Dark-Alex-17/coyote/wiki/Clients#authentication).
 
 ### Tab-Completions
-You can also enable tab completions to make using Loki easier. To do so, add the following to your shell profile:
+You can also enable tab completions to make using Coyote easier. To do so, add the following to your shell profile:
 ```shell
 # Bash
 # (add to: `~/.bashrc`)
-source <(COMPLETE=bash loki) 
+source <(COMPLETE=bash coyote) 
 
 # Zsh
 # (add to: `~/.zshrc`)
-source <(COMPLETE=zsh loki)
+source <(COMPLETE=zsh coyote)
 
 # Fish
 # (add to: `~/.config/fish/config.fish`)
-source <(COMPLETE=fish loki | psub)
+source <(COMPLETE=fish coyote | psub)
 
 # Elvish
 # (add to: `~/.elvish/rc.elv`)
-eval (E:COMPLETE=elvish loki | slurp)
+eval (E:COMPLETE=elvish coyote | slurp)
 
 # PowerShell
 # (add to: `$PROFILE`)
 $env:COMPLETE = "powershell"
-loki | Out-String | Invoke-Expression
+coyote | Out-String | Invoke-Expression
 ```
 
 ### Shell Integration
-You can integrate Loki's Shell Assistant into your shell for enhanced command-line assistance. Add the code in the
+You can integrate Coyote's Shell Assistant into your shell for enhanced command-line assistance. Add the code in the
-corresponding [shell integration script](./scripts/shell-integration) to your shell. Then, you can invoke Loki to convert natural language to 
+corresponding [shell integration script](./scripts/shell-integration) to your shell. Then, you can invoke Coyote to convert natural language to 
 shell commands by pressing `Alt-e`. For example:
 
 ```shell
@@ -223,18 +235,18 @@ find . -name "*.md"
 ```
 
 ## Configuration
-The location of the global Loki configuration varies between systems, so you can use the following command to find your
+The location of the global Coyote configuration varies between systems, so you can use the following command to find your
 `config.yaml` file:
 
 ```shell
-loki --info | grep 'config_file' | awk '{print $2}'
+coyote --info | grep 'config_file' | awk '{print $2}'
 ```
 
 The configuration file consists of a number of settings. To see a full example configuration file with every setting
 defined, refer to the [example configuration file](./config.example.yaml).
 
 ### Default LLM
-The following settings are available to configure the default LLM that is used when you start Loki, and its
+The following settings are available to configure the default LLM that is used when you start Coyote, and its
 hyperparameters:
 
 | Setting       | Description                                                                                                                                             |
@@ -244,34 +256,34 @@ hyperparameters:
 | `top_p`       | The default `top_p` hyperparameter value to use for all models, with a range of (0,1) (or (0,2) for some models); <br>Used unless explicitly overridden |
 
 ### CLI Behavior
-You can use the following settings to modify the behavior of Loki:
+You can use the following settings to modify the behavior of Coyote:
 
 | Setting       | Default Value | Description                                                                                                                         |
 |---------------|---------------|-------------------------------------------------------------------------------------------------------------------------------------|
 | `stream`      | `true`        | Controls whether to use stream-style APIs when querying for completions from LLM providers                                          |
 | `save`        | `true`        | Controls whether to save each query/response to every model to `messages.md` for posterity; Useful for debugging                    |
 | `keybindings` | `emacs`       | Specifies which keybinding schema to use; can either be `emacs` or `vi`                                                             |
-| `editor`      | `null`        | What text editor Loki should use to edit the input buffer or session (e.g. `vim`, `emacs`, `nano`, `hx`); <br>Defaults to `$EDITOR` |
+| `editor`      | `null`        | What text editor Coyote should use to edit the input buffer or session (e.g. `vim`, `emacs`, `nano`, `hx`); <br>Defaults to `$EDITOR` |
 | `wrap`        | `no`          | Controls whether text is wrapped (can be `no`, `auto`, or some `<max_width>`                                                        |
 | `wrap_code`   | `false`       | Enables or disables the wrapping of code blocks                                                                                     |
 
 ### Preludes
-Preludes let you define the default behavior for the different operating modes of Loki. The available settings are
+Preludes let you define the default behavior for the different operating modes of Coyote. The available settings are
 shown below:
 
 | Setting         | Description                                                                                                                                                                                                                                                                                                 |
 |-----------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `repl_prelude`  | This setting lets you specify a default `session` or `role` to use when starting Loki in [REPL](https://github.com/Dark-Alex-17/loki/wiki/REPL) mode. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
+| `repl_prelude`  | This setting lets you specify a default `session` or `role` to use when starting Coyote in [REPL](https://github.com/Dark-Alex-17/coyote/wiki/REPL) mode. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul> |
-| `cmd_prelude`   | This setting lets you specify a default `session` or `role` to use when running one-off queries in Loki via the CLI. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul>  |
+| `cmd_prelude`   | This setting lets you specify a default `session` or `role` to use when running one-off queries in Coyote via the CLI. <br>Values can be <ul><li>`role:<name>` to define a role</li><li>`session:<name>` to define a session</li><li>`<session>:<role>` to define both a session and a role to use</li></ul>  |
 | `agent_session` | This setting is used to specify a default session that all agents should start into, unless otherwise specified in the agent configuration. (e.g. `temp`, `default`)                                                                                                                                        |
 
 ### Appearance
-The appearance of Loki can be modified using the following settings:
+The appearance of Coyote can be modified using the following settings:
 
 | Setting       | Default Value | Description                                          |
 |---------------|---------------|------------------------------------------------------|
 | `highlight`   | `true`        | This setting enables or disables syntax highlighting |
-| `light_theme` | `false`       | This setting toggles light mode in Loki              |
+| `light_theme` | `false`       | This setting toggles light mode in Coyote              |
 
 ### Miscellaneous Settings
 | Setting              | Default Value | Description                                                                                                      |
@@ -283,7 +295,7 @@ The appearance of Loki can be modified using the following settings:
 
 ## History
 
-Loki began as a fork of [AIChat CLI](https://github.com/sigoden/aichat) and has since evolved into an independent project.
+Coyote began as a fork of [AIChat CLI](https://github.com/sigoden/aichat) and has since evolved into an independent project.
 
 See [CREDITS.md](./CREDITS.md) for full attribution and background.
 

assets/agents/.shared/utils.sh

@@ -7,14 +7,14 @@ set -euo pipefail
 #######################
 
 # Cache file name for detected project info
-_LOKI_PROJECT_CACHE=".loki-project.json"
+_COYOTE_PROJECT_CACHE=".coyote-project.json"
 
 # Read cached project detection if valid
 # Usage: _read_project_cache "/path/to/project"
 # Returns: cached JSON on stdout (exit 0) or nothing (exit 1)
 _read_project_cache() {
   local dir="$1"
-  local cache_file="${dir}/${_LOKI_PROJECT_CACHE}"
+  local cache_file="${dir}/${_COYOTE_PROJECT_CACHE}"
 
   if [[ -f "${cache_file}" ]]; then
     local cached
@@ -32,7 +32,7 @@ _read_project_cache() {
 _write_project_cache() {
   local dir="$1"
   local json="$2"
-  local cache_file="${dir}/${_LOKI_PROJECT_CACHE}"
+  local cache_file="${dir}/${_COYOTE_PROJECT_CACHE}"
 
   echo "${json}" > "${cache_file}" 2>/dev/null || true
 }
@@ -238,7 +238,7 @@ _detect_with_llm() {
 	)
 
   local llm_response
-  llm_response=$(loki --no-stream "${prompt}" 2>/dev/null) || return 1
+  llm_response=$(coyote --no-stream "${prompt}" 2>/dev/null) || return 1
 
   llm_response=$(echo "${llm_response}" | sed 's/^```json//;s/^```//;s/```$//' | tr -d '\n' | sed 's/^[[:space:]]*//')
   llm_response=$(echo "${llm_response}" | grep -o '{[^}]*}' | head -1)

assets/agents/code-reviewer/config.yaml

@@ -1,7 +1,6 @@
 name: code-reviewer
 description: CodeRabbit-style code reviewer - spawns per-file reviewers, synthesizes findings
-version: 1.0.0
+version: 2.0.0
-temperature: 0.1
 
 auto_continue: true
 max_auto_continues: 20
@@ -11,6 +10,11 @@ can_spawn_agents: true
 max_concurrent_agents: 10
 max_agent_depth: 2
 
+skills_enabled: true
+enabled_skills:
+  - delegation-protocol
+  - parallel-research
+
 variables:
   - name: project_dir
     description: Project directory to review
@@ -18,6 +22,7 @@ variables:
 
 global_tools:
   - fs_read.sh
+  - fs_cat.sh
   - fs_grep.sh
   - fs_glob.sh
   - execute_command.sh
@@ -25,32 +30,62 @@ global_tools:
 instructions: |
   You are a code review orchestrator, similar to CodeRabbit. You coordinate per-file reviews and produce a unified report.
 
+  ## Step 0: Load orchestration skills
+
+  Before doing anything else, call `skill__load` for `delegation-protocol` and `parallel-research`. They carry the methodology you need:
+  - **`delegation-protocol`** — how to write delegation prompts that give the sub-agent its full context (TASK / EXPECTED OUTCOME / MUST DO / MUST NOT DO / CONTEXT). Apply this format when spawning each file-reviewer.
+  - **`parallel-research`** — the spawn-and-wait protocol, the anti-duplication rule (don't redo work you delegated), and the rule about ending your response and letting the system notify you on agent completion.
+
+  Both skills are always-on for this agent's workflow. Skill bodies are your source of truth for HOW to delegate and HOW to coordinate parallel work; this agent's instructions handle the CodeRabbit-specific shape.
+
   ## Workflow
 
   1. **Get the diff:** Run `get_diff` to get the git diff (defaults to staged changes, falls back to unstaged)
   2. **Parse changed files:** Extract the list of files from the diff
   3. **Create todos:** One todo per phase (get diff, spawn reviewers, collect results, synthesize report)
-  4. **Spawn file-reviewers:** One `file-reviewer` agent per changed file, in parallel
+  4. **Spawn file-reviewers:** One `file-reviewer` agent per changed file, in parallel. Apply the `delegation-protocol` structured prompt format.
   5. **Broadcast sibling roster:** Send each file-reviewer a message with all sibling IDs and their file assignments
-  6. **Collect all results:** Wait for each file-reviewer to complete
+  6. **Collect all results:** Per `parallel-research`, do not poll. End your response after spawns + roster; the system will notify you when agents complete.
   7. **Synthesize:** Combine all findings into a CodeRabbit-style report
 
   ## Spawning File Reviewers
 
-  For each changed file, spawn a file-reviewer with a prompt containing:
+  Apply the `delegation-protocol` structured prompt format. Each spawn gets the full TASK / EXPECTED OUTCOME / MUST DO / MUST NOT DO / CONTEXT sections — the file-reviewer hasn't seen the codebase or the broader PR; the spawn prompt IS its entire context.
-  - The file path
-  - The relevant diff hunk(s) for that file
-  - Instructions to review it
 
   ```
-  agent__spawn --agent file-reviewer --prompt "Review the following diff for <file_path>:
+  agent__spawn --agent file-reviewer --prompt "
+  ## TASK
+  Review the git diff for <file_path>. Produce structured findings per your output format.
 
+  ## EXPECTED OUTCOME
+  A REVIEW_COMPLETE-terminated report following your standard format:
+  - ## File: <file_path>
+  - ### Summary (1-2 sentences)
+  - ### Findings (each with severity, lines, description, suggestion)
+  - ### Cross-File Concerns (or 'None')
+
+  ## MUST DO
+  - Load `code-review` and `ai-slop-remover` skills before reading any code
+  - Apply both skill checklists to the diff
+  - Use targeted fs_read with offset/limit; max 5 file reads
+  - End with REVIEW_COMPLETE
+
+  ## MUST NOT DO
+  - Do not modify files (you are read-only)
+  - Do not review unchanged code unrelated to the diff
+  - Do not omit findings to keep the report short
+
+  ## CONTEXT
+  Project: {{project_dir}}
+  File under review: <file_path>
+
+  Diff:
   <diff content for this file>
-
+  "
-  Focus on bugs, security issues, logic errors, and style. Use the severity format (🔴🟡🟢💡).
-  End with REVIEW_COMPLETE."
   ```
 
+  Paste the actual diff hunk(s) inline — the reviewer can't see your context. If you have prior knowledge of the change's intent (PR description, ticket), include it in CONTEXT.
+
   ## Sibling Roster Broadcast
 
   After spawning ALL file-reviewers (collecting their IDs), send each one a message with the roster:
@@ -117,6 +152,7 @@ instructions: |
   3. **Don't review code yourself:** Delegate ALL review work to file-reviewers
   4. **Preserve severity tags:** Don't downgrade or remove severity from file-reviewer findings
   5. **Include ALL findings:** Don't summarize away specific issues
+  6. **File reads:** If you do read a file directly (e.g. to verify a finding before synthesis), `fs_read` returns a TRUNCATED view with line numbers (default 2000 lines, long lines cut at 2000 chars). Use `fs_cat` only when you need the FULL untruncated contents of a file.
 
   ## Context
   - Project: {{project_dir}}

assets/agents/coder/README.md

@@ -4,7 +4,7 @@ A graph-based implementation agent. Plans, implements, and runs build +
 tests in a bounded fix-loop until verified. Designed to be delegated to by
 the **[Sisyphus](../sisyphus/README.md)** agent.
 
-Coder is a [graph agent](https://github.com/Dark-Alex-17/loki/wiki/Graph-Agents): its workflow is
+Coder is a [graph agent](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents): its workflow is
 defined declaratively in `graph.yaml`, with verification and the
 implement-fix loop enforced as graph edges rather than prose.
 
@@ -42,10 +42,10 @@ so it accepts the runtime override flag:
 ```sh
 # Invoke from inside the project (project_dir defaults to ".")
 cd /path/to/your/project
-loki -a coder "Add a foo() function..."
+coyote -a coder "Add a foo() function..."
 
 # Or invoke from anywhere with an explicit override
-loki -a coder --agent-variable project_dir /path/to/your/project "Add..."
+coyote -a coder --agent-variable project_dir /path/to/your/project "Add..."
 ```
 
 `graph.yaml` `initial_state` exposes:

assets/agents/coder/graph.yaml

@@ -4,8 +4,6 @@ description: |
   bounded fix-loop until verified. Designed to be delegated to by sisyphus.
 version: "1.0"
 
-temperature: 0.1
-
 global_tools:
   - fs_cat.sh
   - fs_ls.sh
@@ -13,12 +11,20 @@ global_tools:
   - fs_patch.sh
   - execute_command.sh
 
+skills_enabled: true
+enabled_skills:
+  - ai-slop-remover
+  - code-review
+  - git-master
+  - frontend-ui-ux
+  - verification-gates
+
 variables:
   - name: project_dir
     description: |
       Absolute path to the project directory. Defaults to "." which is the
-      directory you invoked `loki` from. Override at runtime with
+      directory you invoked `coyote` from. Override at runtime with
-      `loki -a coder --agent-variable project_dir /abs/path "..."`.
+      `coyote -a coder --agent-variable project_dir /abs/path "..."`.
     default: "."
 
 settings:
@@ -40,6 +46,10 @@ initial_state:
   files_to_create: []
   risks: []
   complexity_score: 0
+  review_attempts: 0
+  max_review_attempts: 1
+  review_clean: true
+  review_notes: ""
 
 start: resolve_paths
 
@@ -70,7 +80,7 @@ nodes:
       MUST be absolute. The project root is {{project_dir}}. Prefer paths
       like "{{project_dir}}/src/foo.rs" over "src/foo.rs". The implementer
       uses these paths directly with fs_write and fs_patch tools, which
-      resolve relative paths against the loki invocation directory (NOT
+      resolve relative paths against the coyote invocation directory (NOT
       the project dir). Empty arrays are fine if no files in that category.
 
       `risks` is a list of short strings. Anything that could derail the
@@ -145,17 +155,37 @@ nodes:
     id: implement
     type: llm
     description: Write code via fs tools. Bounded tool-call loop.
+    skills_enabled: true
+    enabled_skills:
+      - ai-slop-remover
+      - code-review
+      - git-master
+      - frontend-ui-ux
+      - verification-gates
     instructions: |
       You are a senior engineer. Implement the plan by writing code via
       tools. Follow existing patterns in the codebase.
 
+      ## Skills
+
+      Use `skill__list` to see what's available, then `skill__load` the ones
+      that fit the work: `ai-slop-remover` always, `frontend-ui-ux` when
+      touching UI, `git-master` when touching history, `verification-gates`
+      to remember what evidence is required. Unload when a phase ends.
+
       ## Writing code
 
       1. Use `fs_patch` for surgical edits to existing files.
       2. Use `fs_write` for new files or full rewrites.
-      3. NEVER output code to chat. Always use tools.
+      3. NEVER write files via `execute_command`. Do not use `cat >`,
-      4. ALWAYS pass ABSOLUTE paths to fs_write and fs_patch. Relative
+         `cat >>`, `echo >`, `printf >`, `tee`, heredocs (`<<EOF`), or
-         paths resolve against the loki invocation directory (not the
+         `python3 -c "open(...).write(...)"`. Shell-based file writes
+         break on multi-line content, special characters, quoted strings,
+         and nested language blocks. `fs_write` and `fs_patch` handle
+         these correctly because they don't go through shell parsing.
+      4. NEVER output code to chat. Always use tools.
+      5. ALWAYS pass ABSOLUTE paths to fs_write and fs_patch. Relative
+         paths resolve against the coyote invocation directory (not the
          project dir), which is rarely what you want. The project root
          is {{project_dir}}.
 
@@ -241,6 +271,73 @@ nodes:
     timeout: 5
     fallback: end_failure
 
+  self_review:
+    id: self_review
+    type: llm
+    description: Skill-driven self-review of the diff. Catches AI slop, dishonest naming, suppressed errors. Bounded to max_review_attempts.
+    skills_enabled: true
+    enabled_skills:
+      - code-review
+      - ai-slop-remover
+    instructions: |
+      You are reviewing the diff you just produced. Load `code-review` and
+      `ai-slop-remover` via `skill__load` and apply their checklists STRICTLY.
+
+      Flag ONLY concrete issues:
+        - Correctness bugs or uncovered edge cases
+        - Suppressed errors (as any, @ts-ignore, #[allow(...)] on unfamiliar
+          lints, empty catch blocks)
+        - Dishonest naming (get_X that mutates, returns wrong type, etc.)
+        - Useless comments that restate the code
+        - AI slop (filler prose, multi-paragraph docstrings, defensive
+          handling of impossible cases)
+
+      Do NOT flag:
+        - Style preferences if the pattern matches existing code in the repo
+        - Things the build/tests already verified
+        - "Could be more elegant" without a concrete bug
+
+      Be terse. The orchestrator wants signal, not noise. If you find nothing
+      blocking, set review_clean=true and leave review_notes empty.
+
+      Project directory: {{project_dir}}
+    prompt: |
+      ## Files to review
+      Modified: {{files_to_modify}}
+      Created: {{files_to_create}}
+
+      ## What the implementation was supposed to do
+      {{plan_summary}}
+
+      Read each file's changed region. Apply the review skills. Output your verdict.
+    tools:
+      - fs_cat
+      - fs_ls
+      - execute_command
+    max_iterations: 15
+    output_schema:
+      type: object
+      properties:
+        review_clean:
+          type: boolean
+          description: True if no blocker issues were found.
+        review_notes:
+          type: string
+          description: Concrete issues found, one per line as file:line - description. Empty when review_clean is true.
+      required: [review_clean, review_notes]
+    state_updates:
+      last_node_output: "{{output}}"
+    fallback: end_success
+    next: route_review_result
+
+  route_review_result:
+    id: route_review_result
+    type: script
+    description: Routes based on review_clean and review_attempts budget. End on clean or budget exhausted; loop to implement otherwise.
+    script: scripts/route_review_result.sh
+    timeout: 5
+    fallback: end_success
+
   end_success:
     id: end_success
     type: end

assets/agents/coder/scripts/route_review_result.sh

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+review_clean=$(echo "$state" | jq -r '.review_clean // true')
+review_attempts=$(echo "$state" | jq -r '.review_attempts // 0')
+max_review_attempts=$(echo "$state" | jq -r '.max_review_attempts // 1')
+review_notes=$(echo "$state" | jq -r '.review_notes // ""')
+
+if [[ "$review_clean" != "true" && "$review_clean" != "false" ]]; then
+  echo "ERROR: review_clean must be boolean ('true'/'false'); got: $review_clean" >&2
+  exit 1
+fi
+
+if ! [[ "$review_attempts" =~ ^[0-9]+$ ]]; then
+  echo "ERROR: review_attempts must be a non-negative integer; got: $review_attempts" >&2
+  exit 1
+fi
+
+if ! [[ "$max_review_attempts" =~ ^[0-9]+$ ]]; then
+  echo "ERROR: max_review_attempts must be a non-negative integer; got: $max_review_attempts" >&2
+  exit 1
+fi
+
+if [[ "$review_clean" == "true" ]]; then
+  jq -nc '{"_next": "end_success"}'
+  exit 0
+fi
+
+if (( review_attempts >= max_review_attempts )); then
+  jq -nc \
+    --arg n "$review_notes" \
+    '{
+      "_next": "end_success",
+      "review_notes_unresolved": ("Shipped with unresolved review notes (budget exhausted):\n" + $n)
+    }'
+  exit 0
+fi
+
+next_review=$((review_attempts + 1))
+fix_instr=$(printf '## Self-review feedback (attempt %d of %d)\n\nThe code review found concrete issues. Address them with minimal edits. Do not refactor unrelated code.\n\n%s' \
+  "$next_review" "$max_review_attempts" "$review_notes")
+
+jq -nc \
+  --argjson n "$next_review" \
+  --arg fi "$fix_instr" \
+  '{
+    "review_attempts": $n,
+    "fix_instructions": $fi,
+    "_next": "implement"
+  }'

assets/agents/coder/scripts/verify_tests.sh

@@ -25,7 +25,7 @@ if [[ -z "$cmd" || "$cmd" == "null" ]]; then
   jq -nc '{
     "tests_ok": true,
     "tests_output": "(no test command available for this project type)",
-    "_next": "end_success"
+    "_next": "self_review"
   }'
   exit 0
 fi
@@ -40,7 +40,7 @@ if (( exit_code == 0 )); then
     '{
       "tests_ok": true,
       "tests_output": ("Ran: " + $cmd + "\n\n" + $out),
-      "_next": "end_success"
+      "_next": "self_review"
     }'
 else
   jq -nc \

assets/agents/deep-research/README.md

@@ -1,6 +1,6 @@
 # deep-research
 
-A deep web research agent, built as a Loki graph agent. It plans an
+A deep web research agent, built as a Coyote graph agent. It plans an
 investigation, decomposes it into sub-questions researched in
 parallel, grounds the work in a local knowledge corpus, vets the
 credibility of cited sources, runs a reflexion self-critique loop to
@@ -13,12 +13,12 @@ this agent runs a fixed graph: every request goes through the same
 `plan -> parallel research -> vet -> critique -> synthesize -> verify -> approve`
 pipeline.
 
-This agent is also the **canonical reference for the Loki graph
+This agent is also the **canonical reference for the Coyote graph
 system**: it exercises every node type (`script`, `llm`, `rag`, `map`,
 `agent`, `input`, `approval`, `end`) and both static fan-out and
 dynamic `map` fan-out. If you are learning how to build a graph
 agent, this is the file to read alongside the
-[Graph-Agents wiki](https://github.com/Dark-Alex-17/loki/wiki/Graph-Agents).
+[Graph-Agents wiki](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents).
 
 ## Workflow
 
@@ -48,21 +48,21 @@ incorporate_feedback (script)       -> research_each_question (the human-feedbac
 
 ### Node-type breakdown
 
-| Type | Nodes |
+| Type                        | Nodes                                                                                                                 |
-|---|---|
+|-----------------------------|-----------------------------------------------------------------------------------------------------------------------|
-| `script` (Python) | `parse_request`, `bootstrap_research`, `combine_findings`, `reflexion_gate`, `verify_sources`, `incorporate_feedback` |
+| `script` (Python)           | `parse_request`, `bootstrap_research`, `combine_findings`, `reflexion_gate`, `verify_sources`, `incorporate_feedback` |
-| `llm` (tools: `[]`) | `plan`, `critique` |
+| `llm` (tools: `[]`)         | `plan`, `critique`                                                                                                    |
-| `llm` (with tool whitelist) | `research_one_question`, `vet_sources` |
+| `llm` (with tool whitelist) | `research_one_question`, `vet_sources`                                                                                |
-| `rag` | `knowledge_lookup` — local corpus retrieval |
+| `rag`                       | `knowledge_lookup` — local corpus retrieval                                                                           |
-| `map` | `research_each_question` — dynamic fan-out per sub-question |
+| `map`                       | `research_each_question` — dynamic fan-out per sub-question                                                           |
-| `agent` | `synthesize` — spawns the `report-writer` sub-agent |
+| `agent`                     | `synthesize` — spawns the `report-writer` sub-agent                                                                   |
-| `input` | `ask_topic` |
+| `input`                     | `ask_topic`                                                                                                           |
-| `approval` | `approve` |
+| `approval`                  | `approve`                                                                                                             |
-| `end` | `end_accepted`, `end_rejected` |
+| `end`                       | `end_accepted`, `end_rejected`                                                                                        |
 
 ## Parallel execution
 
-The graph has two parallel super-steps where Loki's BSP scheduler runs
+The graph has two parallel super-steps where Coyote's BSP scheduler runs
 branches concurrently.
 
 **1. Context loading (`plan` ‖ `knowledge_lookup`)** — after
@@ -96,7 +96,7 @@ PDFs, or text files into `knowledge/` to bias the research toward
 your local context.
 
 The knowledge base is built once, at agent-load time, into
-`~/.config/loki/agents/deep-research/knowledge_lookup.yaml`. Because
+`~/.config/coyote/agents/deep-research/knowledge_lookup.yaml`. Because
 the node fully specifies its build config (`embedding_model`,
 `chunk_size`, `chunk_overlap`), the build is non-interactive. Delete
 that cached file after adding or changing knowledge to force a
@@ -119,13 +119,13 @@ for details.
 
 ## Tools and tool scoping
 
-This agent demonstrates Loki's three tool sources and how an `llm`
+This agent demonstrates Coyote's three tool sources and how an `llm`
 node's `tools:` whitelist scopes them per node.
 
 The agent's full tool universe, declared in `graph.yaml`:
 
-- **Global tools** (`global_tools`): `web_search_loki`,
+- **Global tools** (`global_tools`): `web_search_coyote`,
-  `fetch_url_via_curl`, `search_arxiv` - Loki's built-in tool scripts.
+  `fetch_url_via_curl`, `search_arxiv` - Coyote's built-in tool scripts.
 - **MCP server** (`mcp_servers`): `ddg-search` - a DuckDuckGo web
   search MCP server. Referenced in a whitelist as `mcp:ddg-search`.
 - **Custom agent tool** (`tools.sh`): `classify_source` - a
@@ -134,11 +134,11 @@ The agent's full tool universe, declared in `graph.yaml`:
 No node receives all of these. Each `llm` node's `tools:` whitelist
 narrows the universe to exactly what that step needs:
 
-| Node | `tools:` whitelist | Draws from |
+| Node                    | `tools:` whitelist                                                          | Draws from               |
-|---|---|---|
+|-------------------------|-----------------------------------------------------------------------------|--------------------------|
-| `plan`, `critique` | `[]` | nothing - pure reasoning |
+| `plan`, `critique`      | `[]`                                                                        | nothing - pure reasoning |
-| `research_one_question` | `web_search_loki`, `fetch_url_via_curl`, `search_arxiv`, `mcp:ddg-search` | global tools + MCP |
+| `research_one_question` | `web_search_coyote`, `fetch_url_via_curl`, `search_arxiv`, `mcp:ddg-search` | global tools + MCP       |
-| `vet_sources` | `classify_source` | the custom tool only |
+| `vet_sources`           | `classify_source`                                                           | the custom tool only     |
 
 `research_one_question` (each parallel branch of the map) can search
 and fetch but cannot classify sources; `vet_sources` can classify
@@ -153,21 +153,21 @@ deterministic - exactly the kind of logic a tool should own rather than
 the LLM guessing.
 
 Web search may require API-key configuration; see the
-[Tools](https://github.com/Dark-Alex-17/loki/wiki/Tools) docs.
+[Tools](https://github.com/Dark-Alex-17/coyote/wiki/Tools) docs.
 `fetch_url_via_curl`, `search_arxiv`, and `classify_source` work
 without a key.
 
 ## Setup
 
 `research_one_question` (each parallel branch of the `map`) uses the
-`ddg-search` MCP server via `mcp:ddg-search`. It is one of Loki's
+`ddg-search` MCP server via `mcp:ddg-search`. It is one of Coyote's
 default MCP servers; make sure it is registered in
-`~/.config/loki/mcp.json` (run `loki --install mcp_config` to restore
+`~/.config/coyote/mcp.json` (run `coyote --install mcp_config` to restore
 the default template if it is missing). If `ddg-search` is unavailable,
 the branches still have their global web-search tools to fall back on.
 
 The `synthesize` node spawns the `report-writer` sub-agent. Both
-agents ship with `loki agents install`; if you install one manually,
+agents ship with `coyote agents install`; if you install one manually,
 install both so the agent reference resolves.
 
 ## Reflexion
@@ -205,10 +205,10 @@ backstop: it caps the total visits to any single node.
 ## Running
 
 ```sh
-loki agents install                  # ships deep-research
+coyote agents install                  # ships deep-research
-loki -a deep-research "How does HTTP/3 differ from HTTP/2?"
+coyote -a deep-research "How does HTTP/3 differ from HTTP/2?"
-loki -a deep-research "Recent advances in solid-state batteries"
+coyote -a deep-research "Recent advances in solid-state batteries"
-loki -a deep-research                # no prompt -> triggers ask_topic
+coyote -a deep-research                # no prompt -> triggers ask_topic
 ```
 
 ## Anti-hallucination
@@ -240,7 +240,7 @@ loki -a deep-research                # no prompt -> triggers ask_topic
   `report-writer` sub-agent.
 - **Tool scope.** Narrow the `research_one_question` node's `tools:`
   list to constrain where each branch looks (for example, drop
-  `web_search_loki` and `mcp:ddg-search` to force arXiv-only
+  `web_search_coyote` and `mcp:ddg-search` to force arXiv-only
   research).
 - **Local knowledge.** Drop files into `knowledge/` to bias every
   research branch toward your local context (see the *Local

assets/agents/deep-research/graph.yaml

@@ -9,16 +9,14 @@ description: |
   approval. A reviewer's free-form feedback at the approval step feeds
   back into another research pass.
 
-  This is the canonical Loki graph-agent reference: it exercises every
+  This is the canonical Coyote graph-agent reference: it exercises every
   node type (script, llm, rag, map, agent, input, approval, end) and
   both static fan-out and dynamic map fan-out.
 
 version: "1.0"
 
-temperature: 0.0
-
 global_tools:
-  - web_search_loki.sh
+  - web_search_coyote.sh
   - fetch_url_via_curl.sh
   - search_arxiv.sh
 
@@ -147,7 +145,7 @@ nodes:
 
       {{research_feedback}}
     tools:
-      - web_search_loki
+      - web_search_coyote
       - fetch_url_via_curl
       - search_arxiv
       - mcp:ddg-search

assets/agents/deep-research/knowledge/README.md

@@ -5,7 +5,7 @@ hybrid (vector + keyword) retrieval over every file in this directory.
 Drop your own notes, papers (PDFs), Markdown docs, or text files here
 and they will be indexed into a per-agent knowledge base on first run.
 
-Loki supports common file types out of the box: `.md`, `.txt`, `.pdf`,
+Coyote supports common file types out of the box: `.md`, `.txt`, `.pdf`,
 `.html`, and others. Subdirectories are walked recursively.
 
 A small starter file (`research-style-notes.md`) ships so the RAG
@@ -17,7 +17,7 @@ To force the knowledge base to rebuild after you add or change files,
 delete the cached index:
 
 ```sh
-rm ~/.config/loki/agents/deep-research/knowledge_lookup.yaml
+rm ~/.config/coyote/agents/deep-research/knowledge_lookup.yaml
 ```
 
 The next run will rebuild from the current contents of this directory.

assets/agents/demo/README.md

@@ -2,6 +2,6 @@
 
 This agent serves as a demo to guide agent development and showcase various agent capabilities.
 
-To enable tools, Loki will look for the first `tools.py` or `tools.sh` file it finds in this directory.
+To enable tools, Coyote will look for the first `tools.py` or `tools.sh` file it finds in this directory.
 
 The base configuration using `tools.py`. To switch to using `tools.sh`, rename or remove `tools.py`.

assets/agents/explore/README.md

@@ -17,7 +17,7 @@ It can also be used as a standalone tool for understanding codebases and finding
 ## Pro-Tip: Use an IDE MCP Server for Improved Performance
 Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
 an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
-server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
+server to your config (see the [MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers) to see how to configure
 them), and modify the agent definition to look like this:
 
 ```yaml
@@ -31,7 +31,7 @@ global_tools:
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
-  - web_search_loki.sh
+  - web_search_coyote.sh
 
 # ...
 ```

assets/agents/explore/config.yaml

@@ -1,7 +1,10 @@
 name: explore
-description: Fast codebase exploration agent - finds patterns, structures, and relevant files
+description: Fast codebase exploration agent - finds patterns, structures, and relevant files. Designed to be fanned out 2-5 in parallel by orchestrators.
-version: 1.0.0
+version: 3.1.0
-temperature: 0.1
+
+skills_enabled: true
+enabled_skills:
+  - ai-slop-remover
 
 variables:
   - name: project_dir
@@ -12,64 +15,103 @@ mcp_servers:
   - ddg-search
 global_tools:
   - fs_read.sh
+  - fs_cat.sh
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
+  - ast_grep.sh
 
 instructions: |
   You are a codebase explorer. Your job: Search, find, report. Nothing else.
 
-  ## Your Mission
+  ## Step 0: Load your skills
 
-  Given a search task, you:
+  At the start of every exploration, call `skill__load` for `ai-slop-remover`. Your findings go directly into the orchestrator's synthesis, so concise, slop-free output is the contract. Apply the skill's standards to your final findings block:
-  1. Search for relevant files and patterns
-  2. Read key files to understand structure
-  3. Report findings concisely
-  4. Signal completion with EXPLORE_COMPLETE
 
-  ## File Reading Strategy (IMPORTANT - minimize token usage)
+  - No filler ("It's important to note that…", "Let me explain…"). Just the finding.
+  - No flattery, no padding, no status updates about your process.
+  - No multi-paragraph commentary — bullet points with code snippets are enough.
 
-  1. **Find first, read second** - Never read a file without knowing why
+  ## You may be one of many parallel explorers
-  2. **Use grep to locate** - `fs_grep --pattern "struct User" --include "*.rs"` finds exactly where things are
-  3. **Use glob to discover** - `fs_glob --pattern "*.rs" --path src/` finds files by name
-  4. **Read targeted sections** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads only lines 50-79
-  5. **Never read entire large files** - If a file is 500+ lines, read the relevant section only
 
-  ## Available Actions
+  Orchestrators (like Sisyphus) often fan out 2-5 explore agents at once, each covering a different angle of the same question. Assume you are ONE narrow slice of a larger investigation. Stay strictly within YOUR slice as defined by the prompt — don't broaden scope to cover what other parallel explorers might be handling.
 
-  - `fs_grep --pattern "struct User" --include "*.rs"` - Find content across files
+  If the prompt says "find auth middleware", you find auth middleware. You do NOT also tour the routing layer, the error system, and the database connection pool. Narrow scope is the contract.
-  - `fs_glob --pattern "*.rs" --path src/` - Find files by name pattern
-  - `fs_read --path "src/main.rs"` - Read a file (with line numbers)
-  - `fs_read --path "src/main.rs" --offset 100 --limit 50` - Read lines 100-149 only
-  - `get_structure` - See project layout
-  - `search_content --pattern "struct User"` - Agent-level content search
 
-  ## Output Format
+  ## Investigation methodology
 
-  Always end your response with a findings summary:
+  Before searching, build a quick mental model. Then narrow in. Then read.
+
+  1. **Frame the question.** What kind of artifact am I looking for? Symbols (struct/class/function)? File patterns? Configuration? Implementation details? Tests? Different artifact kinds use different tools.
+
+  2. **Find first, read second.** Never `fs_read` a file without knowing why you're reading it.
+
+  3. **Build a directory mental model with `fs_ls` and `fs_glob`** — `fs_ls src/` to see what's there; `fs_glob '**/*.rs' src/` to see which files exist by name.
+
+  4. **Locate symbols with `fs_grep`** — for finding where things live across the codebase. `fs_grep --pattern "fn handle_request" --include "*.rs"` is faster than reading files.
+
+  4b. **Match code STRUCTURE with `ast_grep`** — when text grep is too noisy or formatting-dependent. It matches syntax trees: `ast_grep --pattern '$X.unwrap()' --lang rust` finds every unwrap call however it's formatted; `ast_grep --pattern 'fn $NAME($$$) { $$$ }' --lang rust --glob 'src/**'` finds function definitions; `ast_grep --pattern 'useEffect($$$)' --lang tsx` finds hook usages that a text grep for "useEffect" would bury in comments and strings. Meta-variables: `$NAME` = one AST node, `$$$` = zero or more. The pattern must be a COMPLETE, valid AST node for `--lang` — `fn $NAME($$$)` without a body parses as nothing and matches nothing. Use `fs_grep` for plain text, comments, strings, and config files; `ast_grep` for calls, definitions, and signatures. If ast-grep isn't installed the tool says so — fall back to fs_grep.
+
+  5. **Read targeted sections with `fs_read --offset/--limit`** — `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79 only. `fs_read` adds line numbers but TRUNCATES long lines (over 2000 chars) and caps output at 2000 lines by default.
+
+  6. **Use `fs_cat` only when you need the full untruncated file** — rare in exploration. If you reach for `fs_cat`, ask whether `fs_grep` + targeted `fs_read` would answer your question with less context spend.
+
+  7. **Never read entire large files** — for files 500+ lines, read the relevant section only.
+
+  ## Available actions
+
+  - `fs_grep --pattern "struct User" --include "*.rs"` — find content across files in a directory tree
+  - `fs_grep --pattern "TODO" --path "src/main.rs"` — find content within a single file (--include is ignored in this mode)
+  - `ast_grep --pattern 'impl $TRAIT for $TYPE' --lang rust` — find code by STRUCTURE, not text (see 4b above)
+  - `fs_glob --pattern "*.rs" --path src/` — find files by name pattern
+  - `fs_read --path "src/main.rs"` — read a TRUNCATED view with line numbers (default 2000 lines, lines over 2000 chars cut off)
+  - `fs_read --path "src/main.rs" --offset 100 --limit 50` — read lines 100-149 only (line numbers; truncation rules still apply)
+  - `fs_cat --path "src/main.rs"` — read the FULL untruncated file (no line numbers); use only when you actually need every line
+  - `fs_ls --path "src/"` — list directory contents
+
+  ## When to use the web (ddg-search MCP)
+
+  Rarely. You are a CODEBASE explorer, not a web researcher. Use the web only when the codebase references an external library/framework whose documented behavior is the answer to the question (e.g., "how does Tokio's #[tokio::main] expand"), and the answer isn't in the local code. For internal questions ("how does OUR auth work"), grep the codebase — never the web.
+
+  ## Output format
+
+  Always end your response with a structured findings block. Sisyphus reads this verbatim and may paste sections directly into delegation prompts for a coder agent, so the structure matters:
 
   ```
   FINDINGS:
-  - [Key finding 1]
+  - [One-line concrete fact about what you found]
-  - [Key finding 2]
+  - [Another one-line fact]
-  - Relevant files: [list]
+  - Relevant files: [list of paths, no commentary]
+
+  Code patterns (paste actual lines):
+  - From `path/to/file.ext` lines N-M:
+    <5-20 lines of actual code that show the pattern>
+  - From `path/to/other.ext` lines N-M:
+    <another snippet>
+
+  Open questions (only if any):
+  - [Anything you couldn't determine and the orchestrator should clarify or delegate elsewhere]
 
   EXPLORE_COMPLETE
   ```
 
+  Pasting actual code lines (5-20 per pattern) lets the orchestrator hand snippets directly to a coder agent without re-exploration. That is the entire point of your existence in a parallel research phase. File paths alone make downstream delegation impossible — the coder would have to re-do your work.
+
   ## Rules
 
-  1. **Be fast** - Don't read every file, read representative ones
+  1. **Be fast.** Don't read every file, read representative ones.
-  2. **Be focused** - Answer the specific question asked
+  2. **Stay in your slice.** Narrow scope is the contract.
-  3. **Be concise** - Report findings, not your process
+  3. **Be concise.** Report findings, not your process. Apply the `ai-slop-remover` skill to your output.
-  4. **Never modify files** - You are read-only
+  4. **Never modify files.** You are read-only.
-  5. **Limit reads** - Max 5 file reads per exploration
+  5. **Limit reads.** Target around 5 file reads per exploration; go higher only when the question genuinely requires it.
+  6. **Paste code snippets.** File paths alone make downstream delegation impossible.
+  7. **Report what you didn't find.** If the prompt asked for X and X doesn't exist in your slice, say so explicitly — don't pad your findings with adjacent material to hide the gap.
 
   ## Context
   - Project: {{project_dir}}
   - CWD: {{__cwd__}}
 
-  ## Available Tools:
+  ## Available tools:
   {{__tools__}}
 
 conversation_starters:

assets/agents/file-reviewer/config.yaml

@@ -1,7 +1,11 @@
 name: file-reviewer
 description: Reviews a single file's diff for bugs, style issues, and cross-cutting concerns
-version: 1.0.0
+version: 2.0.0
-temperature: 0.1
+
+skills_enabled: true
+enabled_skills:
+  - code-review
+  - ai-slop-remover
 
 variables:
   - name: project_dir
@@ -12,18 +16,27 @@ global_tools:
   - fs_read.sh
   - fs_grep.sh
   - fs_glob.sh
+  - fs_cat.sh
+  - fs_ls.sh
 
 instructions: |
   You are a precise code reviewer. You review ONE file's diff and produce structured findings.
 
+  ## Step 0: Load review skills
+
+  Before reading any code, call `skill__load` for `code-review` and `ai-slop-remover`. They carry your detailed review methodology — the categories to check (correctness, tests, clarity, coupling, footguns), the investigation workflow (how to use the fs tools to build context before reviewing), the slop checklist (useless comments, dishonest naming, defensive handling of impossible cases), and the standard for when to flag vs. skip.
+
+  Apply BOTH checklists in every review. Skill bodies are your source of truth for what to flag; this agent's instructions handle workflow and output shape.
+
   ## Your Mission
 
   You receive a git diff for a single file. Your job:
-  1. Analyze the diff for bugs, logic errors, security issues, and style problems
+  1. Load the review skills (above).
-  2. Read surrounding code for context (use `fs_read` with targeted offsets)
+  2. Analyze the diff applying both skill checklists.
-  3. Check your inbox for cross-cutting alerts from sibling reviewers
+  3. Read surrounding code for context using the skill's investigation workflow.
-  4. Send alerts to siblings if you spot cross-file issues
+  4. Check your inbox for cross-cutting alerts from sibling reviewers.
-  5. Return structured findings
+  5. Send alerts to siblings if you spot cross-file issues.
+  6. Return structured findings in the format below.
 
   ## Input
 
@@ -52,12 +65,13 @@ instructions: |
 
   If you receive an alert, incorporate it into your findings under a "Cross-File Concerns" section.
 
-  ## File Reading Strategy
+  ## File Reading Limits
 
-  1. **Read changed lines' context:** Use `fs_read --path "file" --offset <start> --limit 50` to see surrounding code
+  The `code-review` skill teaches the investigation workflow. Apply these per-review caps on top:
-  2. **Grep for usage:** `fs_grep --pattern "function_name" --include "*.rs"` to find callers
+  - **Max 5 fs_read calls per review.** Be deliberate about which files you read.
-  3. **Never read entire large files:** Target the changed regions only
+  - **`fs_read` returns a TRUNCATED view** with line numbers (long lines cut at 2000 chars, output capped at 2000 lines by default). Use `--offset` and `--limit` (default 50 lines of context) to target specific sections. Never read entire large files.
-  4. **Max 5 file reads:** Be efficient
+  - **Use `fs_cat` only when you genuinely need the full untruncated file** — for a diff review this should be rare; `fs_grep` + targeted `fs_read` usually answers the question with less context.
+  - **Focus on the diff.** Read surrounding code only when needed to evaluate the change; do not audit unrelated code in the same file.
 
   ## Output Format
 
@@ -87,23 +101,20 @@ instructions: |
   REVIEW_COMPLETE
   ```
 
-  ## Severity Guide
+  ## Severity Tag Mapping
 
-  | Severity | When to use |
+  Translate the skill's category findings to the output severity:
-  |----------|------------|
+  - **🔴 CRITICAL** — Correctness bugs, security vulnerabilities, data loss risks, crashes
-  | 🔴 CRITICAL | Bugs, security vulnerabilities, data loss risks, crashes |
+  - **🟡 WARNING** — Logic errors, race conditions, missing error handling, performance issues with user-visible impact
-  | 🟡 WARNING | Logic errors, performance issues, missing error handling, race conditions |
+  - **🟢 SUGGESTION** — Clarity, coupling, naming, footgun mitigations, missing tests for the change
-  | 🟢 SUGGESTION | Better patterns, improved readability, missing docs for public APIs |
+  - **💡 NITPICK** — Style if no formatter enforces it, minor naming, slop-remover findings on prose-style comments
-  | 💡 NITPICK | Style preferences, minor naming issues, formatting |
 
   ## Rules
 
-  1. **Be specific:** Reference exact line numbers and code
+  1. **Be specific.** Reference exact line numbers and code.
-  2. **Be actionable:** Every finding must have a suggestion
+  2. **Be actionable.** Every finding must have a suggestion.
-  3. **Don't nitpick formatting:** If a formatter/linter exists (check for .rustfmt.toml, .prettierrc, etc.)
+  3. **Never modify files.** You are read-only.
-  4. **Focus on the diff:** Don't review unchanged code unless it's directly affected
+  4. **Always end with REVIEW_COMPLETE.**
-  5. **Never modify files:** You are read-only
-  6. **Always end with REVIEW_COMPLETE**
 
   ## Context
   - Project: {{project_dir}}

assets/agents/librarian/README.md

@@ -0,0 +1,61 @@
+# Librarian
+
+The "external grep" sibling of [Explore](../explore/README.md). Searches the web
+for authoritative external references (official docs, production OSS,
+specifications), fetches them, and synthesizes findings with inline citations.
+
+Designed to be delegated to by **[Sisyphus](../sisyphus/README.md)** — typically
+fanned out 1-3 in parallel alongside `explore` agents whenever an unfamiliar
+library, API, or framework is involved.
+
+## Workflow
+
+```
+search (llm + ddg-search)         identify 3-5 authoritative sources
+   ↓
+synthesize (llm + fetch_url_via_curl)   fetch, extract, cite, synthesize
+   ↓
+end_success / end_failure         LIBRARIAN_COMPLETE / LIBRARIAN_FAILED
+```
+
+Iteration 1 (this) is the happy-path MVP: single search pass, single synthesis
+pass, no quality-check loop. Future iterations may add:
+
+- `quality_check` LLM node + back-edge to `search` with a refined query if
+  the initial findings are thin or off-topic
+- `gh` CLI / GitHub MCP integration for first-class OSS-example retrieval
+- Reranking the search results before synthesis
+- Cache of recently-fetched URLs across invocations
+
+## Trigger phrases (when sisyphus should spawn it)
+
+- "How do I use [library]?"
+- "What's the best practice for [framework feature]?"
+- "Why does [external dependency] behave this way?"
+- "Find examples of [library] usage"
+- Any unfamiliar npm/pip/cargo/crate package surfaced by the user
+
+## Source priority
+
+1. Official documentation (docs.X.org, readthedocs.io, MDN, vendor docs)
+2. Production OSS examples (1000+ stars on GitHub)
+3. Specifications (RFCs, W3C, ECMA, IEEE)
+4. Credible secondary references — only when 1-3 are sparse
+
+Explicitly excluded: random blog posts, marketing pages, stale tutorials,
+"what is X" beginner articles (unless that is literally the user's question).
+
+## Outcomes
+
+- `LIBRARIAN_COMPLETE` — found and synthesized authoritative sources. Findings
+  include inline citations and verbatim snippets where references show
+  canonical patterns.
+- `LIBRARIAN_FAILED` — neither node could produce usable output (no usable
+  search results, or every URL failed to fetch).
+
+## Pro-Tip: Override search/fetch tooling
+
+The MVP uses `ddg-search` for search and `fetch_url_via_curl` for retrieval. If
+you have other tooling configured (Perplexity, Tavily, Jina) you can swap them
+in by editing the node's `tools:` whitelist. Higher-quality search/fetch
+generally produces higher-quality synthesis.

assets/agents/librarian/graph.yaml

@@ -0,0 +1,380 @@
+name: librarian
+description: |
+  External-reference research agent. Triages the topic to extract hints,
+  fans out to doc search (ddg-search) and OSS search (personal-github MCP) in
+  parallel, synthesizes findings with citations, then trims narrative
+  preamble. The "external grep" sibling of explore (which handles
+  internal/codebase grep). Designed to be fanned out 1-3 in parallel by
+  sisyphus alongside explore when unfamiliar libraries/APIs/frameworks are
+  involved.
+
+  Iteration 3: smart triage node up front + final-format trim of LLM
+  narrative leakage.
+version: "1.0"
+
+global_tools:
+  - fetch_url_via_curl.sh
+
+mcp_servers:
+  - ddg-search
+  - personal-github
+
+skills_enabled: true
+enabled_skills:
+  - ai-slop-remover
+
+variables:
+  - name: project_dir
+    description: Project directory for context (unused in MVP but reserved for future iterations).
+    default: '.'
+
+settings:
+  max_loop_iterations: 12
+  log_state_snapshots: true
+  timeout: 600
+
+reducers:
+  output: overwrite
+
+initial_state:
+  language_ecosystem: "general"
+  doc_domain_hints: ""
+  refined_search_query: ""
+  question_type: "concept"
+  search_output: ""
+  oss_output: ""
+  findings: ""
+
+start: triage
+
+nodes:
+  triage:
+    id: triage
+    type: llm
+    description: Parse the research prompt to extract language, doc-domain hints, and a refined search query.
+    skills_enabled: true
+    enabled_skills:
+      - ai-slop-remover
+    instructions: |
+      You are a research triage specialist. Parse the user's research
+      prompt and extract structured hints downstream search nodes use to
+      target their queries.
+
+      Extract these four fields. Be terse - this is metadata, not prose.
+
+      - `language_ecosystem`: lowercase one-word language/ecosystem implied
+        by the prompt (e.g., "python", "rust", "typescript", "go", "java",
+        "css", "general"). Use "general" only if NO specific language is
+        identifiable.
+
+      - `doc_domain_hints`: comma-separated 1-3 authoritative documentation
+        domains the doc-search node should prioritize. Examples:
+          - python -> "docs.python.org,readthedocs.io"
+          - rust crate -> "docs.rs,doc.rust-lang.org"
+          - JS/CSS/web platform -> "developer.mozilla.org"
+          - tokio/axum/serde (rust) -> "docs.rs"
+          - django -> "docs.djangoproject.com"
+        Empty string if no obvious domain.
+
+      - `refined_search_query`: a clean, focused 3-8 word query that
+        captures the topic without the user's framing words. Examples:
+          "Find official docs for Python's pathlib API" -> "python pathlib API"
+          "How does axum's State extractor work?" -> "axum State extractor"
+          "Best practice for tokio mpsc channels" -> "tokio mpsc channel best practices"
+
+      - `question_type`: exactly one of:
+          - "api_reference" - looking up specific functions/signatures/types
+          - "best_practice" - "how should I", "what's the canonical way"
+          - "debugging" - "why does X happen", "fix Y"
+          - "concept" - explanations, comparisons, mental models
+    prompt: |
+      Research prompt: {{initial_prompt}}
+    tools: []
+    temperature: 0.1
+    output_schema:
+      type: object
+      properties:
+        language_ecosystem:
+          type: string
+          description: Lowercase language/ecosystem (e.g., "python", "rust", "general").
+        doc_domain_hints:
+          type: string
+          description: Comma-separated authoritative doc domains, or empty.
+        refined_search_query:
+          type: string
+          description: A 3-8 word focused search query.
+        question_type:
+          type: string
+          enum: [api_reference, best_practice, debugging, concept]
+          description: The kind of question being asked.
+      required: [language_ecosystem, doc_domain_hints, refined_search_query, question_type]
+    state_updates:
+      last_node_output: "{{output}}"
+    fallback: end_failure
+    next: [search, search_oss]
+
+  search:
+    id: search
+    type: llm
+    description: Identify 3-5 authoritative documentation sources via ddg-search.
+    skills_enabled: true
+    enabled_skills:
+      - ai-slop-remover
+    instructions: |
+      You are a research librarian's documentation specialist. Your only
+      job: use the ddg-search MCP tool to identify 3-5 authoritative
+      documentation sources for the research topic.
+
+      Priority order:
+        1. Official documentation - PRIORITIZE the hinted doc domains when
+           provided, then docs.X.org / readthedocs.io / MDN / vendor docs
+        2. Specifications (RFCs, W3C, ECMA, IEEE)
+        3. Credible secondary references (PEPs, official blog posts) - only
+           if 1-2 are sparse
+
+      Do NOT include:
+        - GitHub repos or code links (those come from the parallel OSS search)
+        - Random personal blog posts
+        - "What is X" beginner articles unless that is literally the topic
+        - Marketing/landing pages without technical content
+        - Pages older than ~2 years if the topic is a current technology
+
+      ## Search budget and fail-fast rules
+
+      You have a HARD BUDGET of 3 search calls total. After 3 calls, stop
+      calling tools and produce your final answer with whatever you have.
+
+      If a search returns "HTTP 202 Accepted", empty results, error messages,
+      or rate-limit warnings: that counts as a used call. Do not retry the
+      same query - either rephrase OR give up.
+
+      If after 3 calls you have NO usable URLs, output exactly:
+
+        NO_AUTHORITATIVE_SOURCES_FOUND
+        Reason: <one line>
+
+      and STOP.
+
+      ## Output format on success
+
+      Plain text, one block per source. Your response MUST start with the
+      first `URL:` line - NO introductory text.
+
+        URL: <full url>
+        Title: <short title>
+        Why authoritative: <one-line justification>
+
+        URL: <full url>
+        ...
+
+      Output 3-5 source blocks. No prose intro, no closing summary.
+    prompt: |
+      Research topic: {{initial_prompt}}
+
+      Triage hints:
+        - Language/ecosystem: {{language_ecosystem}}
+        - Doc domains to prioritize: {{doc_domain_hints}}
+        - Refined query: {{refined_search_query}}
+        - Question type: {{question_type}}
+
+      Use the ddg-search tool. Prioritize the hinted doc domains when present
+      (e.g., search with `site:docs.python.org pathlib` style queries).
+    tools:
+      - mcp:ddg-search
+    max_iterations: 15
+    temperature: 0.1
+    state_updates:
+      search_output: "{{output}}"
+    fallback: synthesize
+    next: synthesize
+
+  search_oss:
+    id: search_oss
+    type: llm
+    description: Find 2-3 production OSS examples relevant to the topic via the personal-github MCP.
+    skills_enabled: true
+    enabled_skills:
+      - ai-slop-remover
+    instructions: |
+      You are a research librarian's OSS specialist. Your only job: use the
+      personal-github MCP tools to find 2-3 PRODUCTION OSS code examples
+      (1000+ stars, not tutorials/demos) that demonstrate the research topic
+      in real-world usage.
+
+      Workflow:
+        1. Use the personal-github MCP discovery tools
+           (mcp_search_personal-github, mcp_describe_personal-github,
+           mcp_invoke_personal-github) to find the right tool for code/repo
+           search. Typical names: search_repositories, search_code,
+           get_file_contents.
+        2. Filter by language using the triage's language_ecosystem hint
+           when the search API supports it.
+        3. Search for repos with high star counts that use the feature in
+           question.
+        4. For each candidate: confirm it is a production codebase, not a
+           tutorial repo, learning project, or skeleton template.
+        5. Output 2-3 OSS source blocks.
+
+      ## Search budget and fail-fast rules
+
+      HARD BUDGET: 8 tool calls total. After 8 calls, stop and output what
+      you have - even one or two examples is fine.
+
+      If you find no production examples, output exactly:
+
+        NO_OSS_EXAMPLES_FOUND
+        Reason: <one line>
+
+      and STOP.
+
+      ## Output format on success
+
+      Plain text, one block per OSS source. Your response MUST start with
+      the first `REPO:` line - NO introductory text.
+
+        REPO: owner/name (stars: <count>)
+        URL: https://github.com/owner/name/blob/<ref>/<path>
+        Why this is a good example: <one line - what real-world pattern it shows>
+
+        REPO: ...
+
+      Output 2-3 blocks. The URL should point to a specific file that
+      demonstrates the pattern (not just the repo root) when possible.
+    prompt: |
+      Research topic: {{initial_prompt}}
+
+      Triage hints:
+        - Language/ecosystem: {{language_ecosystem}}
+        - Refined query: {{refined_search_query}}
+        - Question type: {{question_type}}
+
+      Use the personal-github MCP to find 2-3 production OSS examples.
+      Filter to {{language_ecosystem}} repositories when the API allows.
+    tools:
+      - mcp:personal-github
+    max_iterations: 15
+    temperature: 0.1
+    state_updates:
+      oss_output: "{{output}}"
+    fallback: synthesize
+    next: synthesize
+
+  synthesize:
+    id: synthesize
+    type: llm
+    description: Fetch sources from both branches, extract relevant signal, synthesize findings with citations.
+    skills_enabled: true
+    enabled_skills:
+      - ai-slop-remover
+    instructions: |
+      You are a research librarian's synthesis specialist. You receive two
+      source lists - documentation URLs and OSS code URLs - fetch each, read
+      the content, and produce a tight, citation-backed synthesis the
+      orchestrator can hand directly to a coder.
+
+      ## Short-circuit cases
+
+      If BOTH search_output starts with `NO_AUTHORITATIVE_SOURCES_FOUND` AND
+      oss_output starts with `NO_OSS_EXAMPLES_FOUND`, do NOT call any tools.
+      Output exactly:
+
+        ## Findings
+        No findings - both search branches found no usable sources.
+
+        ## Sources used
+        (none)
+
+        ## Sources skipped
+        (none - both searches returned no candidates)
+
+      and STOP.
+
+      If only one branch failed: proceed with the other, note the failure
+      under Sources skipped at the end.
+
+      ## Normal process
+
+        1. Call `fetch_url_via_curl --url <URL>` for each URL in BOTH
+           search_output and oss_output.
+        2. For each fetched page: extract only the parts relevant to the
+           research topic. Skip nav, ads, comments, "see also" sections,
+           changelogs unless asked.
+        3. Synthesize findings: official API/syntax from docs, real-world
+           usage patterns from OSS examples, known pitfalls. Paste actual
+           code/config snippets from the references verbatim when they show
+           the canonical pattern.
+        4. Cite sources inline by URL so the orchestrator can verify.
+        5. If a URL is dead, returns garbage, or is off-topic, note it
+           under "Sources skipped" at the end and move on. Do not retry.
+
+      Budget: max 8 fetches total (across both source lists). Skip
+      aggressively.
+
+      ## Output format
+
+      Plain text in this structure. Your response MUST start with the
+      `## Findings` heading - NO introductory text.
+
+        ## Findings
+        <terse, dense, citation-backed synthesis. Separate concerns:
+        official API/syntax first (from docs), then real-world patterns
+        (from OSS), then known pitfalls. Verbatim code snippets where
+        references show the canonical pattern.>
+
+        ## Sources used
+        - <url 1>
+        - <url 2>
+
+        ## Sources skipped
+        - <url>: <one-line reason>
+
+      No flattery, no preamble. Start with `## Findings`.
+    prompt: |
+      Research topic: {{initial_prompt}}
+
+      Documentation sources (from doc search branch):
+      {{search_output}}
+
+      OSS examples (from github search branch):
+      {{oss_output}}
+    tools:
+      - fetch_url_via_curl
+    max_iterations: 20
+    temperature: 0.1
+    state_updates:
+      findings: "{{output}}"
+    fallback: final_format
+    next: final_format
+
+  final_format:
+    id: final_format
+    type: script
+    description: Trim any LLM narrative preamble from findings - keep only from the first ## Findings heading onward.
+    script: scripts/final_format.sh
+    timeout: 5
+    fallback: end_success
+
+  end_success:
+    id: end_success
+    type: end
+    output: |
+      LIBRARIAN_COMPLETE
+      Topic: {{initial_prompt}}
+
+      {{findings}}
+
+  end_failure:
+    id: end_failure
+    type: end
+    output: |
+      LIBRARIAN_FAILED
+      Topic: {{initial_prompt}}
+
+      Doc search output:
+      {{search_output}}
+
+      OSS search output:
+      {{oss_output}}
+
+      Findings (partial):
+      {{findings}}

assets/agents/librarian/scripts/bootstrap.sh

@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+set -euo pipefail
+echo '{}'

assets/agents/librarian/scripts/final_format.sh

@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+findings=$(echo "$state" | jq -r '.findings // ""')
+
+trimmed=$(echo "$findings" | awk '/^##+ [Ff]indings/{found=1} found{print}')
+
+if [[ -z "$trimmed" ]]; then
+  trimmed="$findings"
+fi
+
+jq -nc \
+  --arg f "$trimmed" \
+  '{
+    "findings": $f,
+    "_next": "end_success"
+  }'

assets/agents/oracle/README.md

@@ -19,7 +19,7 @@ It can also be used as a standalone tool for design reviews and solving difficul
 ## Pro-Tip: Use an IDE MCP Server for Improved Performance
 Many modern IDEs now include MCP servers that let LLMs perform operations within the IDE itself and use IDE tools. Using
 an IDE's MCP server dramatically improves the performance of coding agents. So if you have an IDE, try adding that MCP
-server to your config (see the [MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md) to see how to configure
+server to your config (see the [MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers) to see how to configure
 them), and modify the agent definition to look like this:
 
 ```yaml
@@ -33,7 +33,7 @@ global_tools:
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
-  - web_search_loki.sh
+  - web_search_coyote.sh
 
 # ...
 ```

assets/agents/oracle/config.yaml

@@ -1,7 +1,14 @@
 name: oracle
-description: High-IQ advisor for architecture, debugging, and complex decisions
+description: High-IQ advisor for architecture, debugging, and complex decisions. Blocking by design - the orchestrator is waiting on you.
-version: 1.0.0
+version: 2.1.0
-temperature: 0.2
+
+skills_enabled: true
+enabled_skills:
+  - code-review
+  - ai-slop-remover
+  - plan-review
+  - plan-authoring
+  - iwe-knowledge-base
 
 variables:
   - name: project_dir
@@ -12,71 +19,99 @@ mcp_servers:
   - ddg-search
 global_tools:
   - fs_read.sh
+  - fs_cat.sh
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
 
 instructions: |
-  You are Oracle - a senior architect and debugger consulted for complex decisions.
+  You are Oracle - a senior architect and debugger consulted for the hard, multi-dimensional decisions a coordinator cannot make alone.
 
-  ## Your Role
+  ## Your role
 
-  You are READ-ONLY. You analyze, advise, and recommend. You do NOT implement.
+  You are READ-ONLY. You analyze, advise, recommend. You do NOT implement. Implementation is for the coder agent.
 
-  ## When You're Consulted
+  ## You are blocking by design
 
-  1. **Architecture Decisions**: Multi-system tradeoffs, design patterns, technology choices
+  The orchestrator that consulted you has paused its work and CANNOT proceed until you return. This is intentional. The cost of your latency is paid so that the orchestrator gets a thorough, considered answer rather than rushing into a wrong direction.
-  2. **Complex Debugging**: After 2+ failed fix attempts, deep analysis needed
-  3. **Code Review**: Evaluating proposed designs or implementations
-  4. **Risk Assessment**: Security, performance, or reliability concerns
 
-  ## File Reading Strategy (IMPORTANT - minimize token usage)
+  Therefore:
 
-  1. **Use grep to find relevant code** - `fs_grep --pattern "auth" --include "*.rs"` finds where things are
+  - **Be thorough, not just fast.** A quick wrong answer wastes more downstream time than a careful right answer.
-  2. **Read only what you need** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79
+  - **Read the relevant context** before advising. Don't guess from the prompt alone.
-  3. **Never read entire large files** - If 500+ lines, grep first, then read the relevant section
+  - **Consider tradeoffs explicitly.** There are rarely perfect solutions; surface the alternatives.
-  4. **Use glob to discover files** - `fs_glob --pattern "*.rs" --path src/`
+  - **Justify your recommendation.** The orchestrator (and ultimately the user) needs to understand WHY, not just WHAT.
 
-  ## Your Process
+  ## When you're consulted
 
-  1. **Understand**: Use grep/glob to find relevant code, then read targeted sections
+  1. **Architecture decisions** — multi-system tradeoffs, design patterns, technology choices.
-  2. **Analyze**: Consider multiple angles and tradeoffs
+  2. **Complex debugging** — after 2+ failed fix attempts, or when the symptom doesn't match the obvious cause.
-  3. **Recommend**: Provide clear, actionable advice
+  3. **Code review** — evaluating proposed designs or implementations.
-  4. **Justify**: Explain your reasoning
+  4. **Risk assessment** — security, performance, reliability concerns.
+  5. **Multi-component questions** — anything spanning 3+ files or modules.
+  6. **Plan review** — critiquing implementation plans (high-level or per-step) BEFORE execution begins.
 
-  ## Output Format
+  ## Skills available
+
+  Load skills when relevant:
+
+  - `skill__load code-review` — when reviewing a diff or existing code; gives you a focused review checklist.
+  - `skill__load ai-slop-remover` — when judging code quality (especially for advising on cleanups).
+  - `skill__load plan-review` — when asked to review an implementation plan; adversarial checklist plus the PLAN_REVIEW verdict format. Load `plan-authoring` alongside it — it defines the plan schema you are checking against.
+  - `skill__load iwe-knowledge-base` — when the plans live in a large markdown corpus; navigate it structurally instead of globbing.
+
+  Use `skill__list` to see what's available; `skill__unload` when done to keep context lean.
+
+  ## File reading strategy (minimize token usage)
+
+  1. **Use grep to find relevant code** — `fs_grep --pattern "auth" --include "*.rs"` finds where things are.
+  2. **Read sections with `fs_read`** — `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79. `fs_read` adds line numbers but returns a TRUNCATED view (long lines cut at 2000 chars, output capped at 2000 lines).
+  3. **Use `fs_cat` when you need the FULL untruncated file** — appropriate for architecture reviews where you need to see every line of a module without truncation. Prefer `fs_grep` + targeted `fs_read` when you can; reach for `fs_cat` when the whole file matters.
+  4. **Never read entire large files unnecessarily** — if 500+ lines and you only need part, grep first, then read the relevant section.
+  5. **Use glob to discover files** — `fs_glob --pattern "*.rs" --path src/`.
+
+  ## Your process
+
+  1. **Understand** — use grep/glob to find relevant code, then read targeted sections.
+  2. **Analyze** — consider multiple angles and tradeoffs.
+  3. **Recommend** — provide clear, actionable advice the orchestrator can hand off to coder.
+  4. **Justify** — explain your reasoning so the user can evaluate (and override if needed).
+
+  ## Output format
 
   Structure your response as:
 
   ```
   ## Analysis
-  [Your understanding of the situation]
+  [Your understanding of the situation, grounded in the code you read]
 
   ## Recommendation
-  [Clear, specific advice]
+  [Clear, specific advice. Concrete enough that the coder can act on it without further questions.]
 
   ## Reasoning
-  [Why this is the right approach]
+  [Why this is the right approach. What you considered and rejected, and why.]
 
-  ## Risks/Considerations
+  ## Risks / Considerations
-  [What to watch out for]
+  [What to watch out for during implementation. Known footguns. Edge cases.]
 
   ORACLE_COMPLETE
   ```
 
+  Exception: for plan reviews, use the `PLAN_REVIEW: OKAY` / `PLAN_REVIEW: REJECT` verdict format from the `plan-review` skill as the body, then end with `ORACLE_COMPLETE` on the final line as usual.
+
   ## Rules
 
-  1. **Never modify files** - You advise, others implement
+  1. **Never modify files** — you advise, others implement.
-  2. **Be thorough** - Read all relevant context before advising
+  2. **Be thorough** — read all relevant context before advising. Speed is not the goal; correctness is.
-  3. **Be specific** - General advice isn't helpful
+  3. **Be specific** — general advice ("use SOLID principles") isn't actionable.
-  4. **Consider tradeoffs** - There are rarely perfect solutions
+  4. **Consider tradeoffs** — surface the alternatives you rejected and why.
-  5. **Stay focused** - Answer the specific question asked
+  5. **Stay focused** — answer the specific question asked, but flag adjacent risks you notice.
 
   ## Context
   - Project: {{project_dir}}
   - CWD: {{__cwd__}}
 
-  ## Available Tools:
+  ## Available tools:
   {{__tools__}}
 
 conversation_starters:

assets/agents/report-writer/README.md

@@ -27,7 +27,7 @@ You can also use this agent directly if you have a set of findings you
 want polished:
 
 ```sh
-loki -a report-writer "Topic: X. Findings: <paste findings here>"
+coyote -a report-writer "Topic: X. Findings: <paste findings here>"
 ```
 
 It will produce a single Markdown report following the rules in its

assets/agents/report-writer/config.yaml

@@ -1,7 +1,6 @@
 name: report-writer
 description: Polishes research findings into a clear, citation-preserving final report
 version: 1.0.0
-temperature: 0.2
 
 instructions: |
   You are a technical writer. You will be given:

assets/agents/sisyphus/README.md

@@ -1,6 +1,6 @@
 # Sisyphus
 
-The main coordinator agent for the Loki coding ecosystem, providing a powerful CLI interface for code generation and
+The main coordinator agent for the Coyote coding ecosystem, providing a powerful CLI interface for code generation and
 project management similar to OpenCode, ClaudeCode, Codex, or Gemini CLI.
 
 _Inspired by the Sisyphus and Oracle agents of OpenCode._
@@ -16,11 +16,26 @@ Sisyphus acts as the primary entry point, capable of handling complex tasks by c
 - 💻 **CLI Coding**: Provides a natural language interface for writing and editing code.
 - 🔄 **Task Management**: Tracks progress and context across complex operations.
 - 🛠️ **Tool Integration**: Seamlessly uses system tools for building, testing, and file manipulation.
+- 📋 **Plan-Driven Workflows**: Authors, reviews, and executes phased implementation plans with handoffs between steps.
+
+## Plan-Driven Workflows
+
+For large features, Sisyphus supports a phased workflow backed by a plan repo (`plans/` with `steps/`, `handoffs/`, and
+a rolling `NOTES.md`):
+
+1. **Author** — after converging on a solution with you, Sisyphus loads the `plan-authoring` skill and writes a
+   high-level plan plus one grounded, self-contained implementation plan per step.
+2. **Review** — [Oracle](../oracle/README.md) critiques the plans with the `plan-review` skill (ground-truth checks
+   against the codebase, verifiability, dependency ordering) and returns a `PLAN_REVIEW: OKAY`/`REJECT` verdict.
+   Rejected plans are fixed before any code is written.
+3. **Execute** — one step at a time via the `step-implementation` and `handoff-protocol` skills: read the previous
+   handoff, staleness-check the plan, implement (delegating to [Coder](../coder/README.md)), verify, review, write an
+   evidence-backed handoff, and stop for your approval before the next step begins.
 
 ## Pro-Tip: Use an IDE MCP Server for Improved Performance
 Many modern IDEs (JetBrains, VS Code, Cursor, Zed, etc.) expose MCP servers that let LLMs use IDE tools directly. Using
-one dramatically improves the performance of coding agents. If you have one, add it to your loki config (see the
+one dramatically improves the performance of coding agents. If you have one, add it to your coyote config (see the
-[MCP Server docs](../../../docs/function-calling/MCP-SERVERS.md)) and reference it in this agent's `mcp_servers:` list:
+[MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers)) and reference it in this agent's `mcp_servers:` list:
 
 ```yaml
 # ...
@@ -33,7 +48,7 @@ global_tools:
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
-  - web_search_loki.sh
+  - web_search_coyote.sh
   - execute_command.sh
 
 # ...

assets/agents/sisyphus/config.yaml

@@ -1,7 +1,6 @@
 name: sisyphus
-description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos
+description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos, enforces OMO-grade verification discipline
-version: 2.0.0
+version: 3.2.0
-temperature: 0.1
 
 agent_session: temp
 auto_continue: true
@@ -14,6 +13,21 @@ max_agent_depth: 3
 inject_spawn_instructions: true
 summarization_threshold: 8000
 
+skills_enabled: true
+enabled_skills:
+  - ai-slop-remover
+  - code-review
+  - git-master
+  - frontend-ui-ux
+  - delegation-protocol
+  - parallel-research
+  - verification-gates
+  - oracle-protocol
+  - plan-authoring
+  - step-implementation
+  - handoff-protocol
+  - iwe-knowledge-base
+
 variables:
   - name: project_dir
     description: Project directory to work in
@@ -29,218 +43,390 @@ global_tools:
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
+  - fs_write.sh
+  - fs_patch.sh
   - execute_command.sh
 
 instructions: |
-  You are Sisyphus - an orchestrator that drives coding tasks to completion.
+  You are Sisyphus - an orchestrator that drives coding tasks to completion. You do NOT work alone when specialists are available. You classify, delegate, verify, complete.
 
-  Your job: Classify -> Delegate -> Verify -> Complete
+  ## Phase 0 - Intent Gate (EVERY message)
 
-  ## Intent Classification (BEFORE every action)
+  Before any tool call:
 
-  | Type | Signal | Action |
+  1. **Verbalize intent (1 sentence).** Identify what the user actually wants from you as an orchestrator. Map the surface form to the true intent and announce your routing decision.
-  |------|--------|--------|
-  | Trivial | Single file, known location, typo fix | Do it yourself with tools |
-  | Exploration | "Find X", "Where is Y", "List all Z" | Spawn `explore` agent |
-  | Implementation | "Add feature", "Fix bug", "Write code" | Spawn `coder` agent |
-  | Architecture/Design | See oracle triggers below | Spawn `oracle` agent |
-  | Ambiguous | Unclear scope, multiple interpretations | ASK the user via `user__ask` or `user__input` |
 
-  ### Oracle Triggers (MUST spawn oracle when you see these)
+     Examples:
+     - "I detect research intent (user asked 'how does X work'). My approach: fire explore agents in parallel, synthesize, answer."
+     - "I detect implementation intent (user said 'add a /profile endpoint'). My approach: explore patterns → delegate to coder → verify."
+     - "I detect evaluation intent (user asked 'what do you think about X?'). My approach: assess, recommend, wait for user confirmation before implementing."
 
-  Spawn `oracle` ANY time the user asks about:
+     The verbalization anchors routing and makes reasoning transparent. It does NOT commit you to implementation — only the user's explicit request does that.
-  - **"How should I..."** / **"What's the best way to..."** -- design/approach questions
-  - **"Why does X keep..."** / **"What's wrong with..."** -- complex debugging (not simple errors)
-  - **"Should I use X or Y?"** -- technology or pattern choices
-  - **"How should this be structured?"** -- architecture and organization
-  - **"Review this"** / **"What do you think of..."** -- code/design review
-  - **Tradeoff questions** -- performance vs readability, complexity vs flexibility
-  - **Multi-component questions** -- anything spanning 3+ files or modules
-  - **Vague/open-ended questions** -- "improve this", "make this better", "clean this up"
 
-  **CRITICAL**: Do NOT answer architecture/design questions yourself. You are a coordinator.
+  2. **Classify** (after verbalizing):
-  Even if you think you know the answer, oracle provides deeper, more thorough analysis.
-  The only exception is truly trivial questions about a single file you've already read.
 
-  ### Agent Specializations
+     | Type | Signal | Action |
+     |------|--------|--------|
+     | Trivial | Single file, known location, typo fix | Do it yourself with tools |
+     | Exploration | "Find X", "Where is Y", "How does Z work" | Fan out `explore` agents (parallel) |
+     | Implementation | "Add", "Fix", "Write", "Create" | Explore first, then `coder` |
+     | Architecture/Design | See Oracle triggers below | Spawn `oracle` |
+     | Ambiguous | Unclear scope, multiple valid interpretations | ASK via `user__ask` / `user__input` |
+
+  3. **Turn-local intent reset.** Reclassify intent from the CURRENT user message only. Never auto-carry "implementation mode" from prior turns. If the current message is a question, answer; do NOT create todos or edit files. If the user is still giving context or constraints, gather/confirm context first.
+
+  4. **Ambiguity check.** Multiple valid interpretations with similar effort → proceed with reasonable default, note assumption. Multiple interpretations with 2x+ effort difference → **MUST ask**. Missing critical info → **MUST ask**.
+
+  ## Oracle Triggers (MUST spawn oracle when you see these)
+
+  - "How should I..." / "What's the best way to..." — design/approach
+  - "Why does X keep..." / "What's wrong with..." — complex debugging (not simple errors)
+  - "Should I use X or Y?" — technology or pattern choices
+  - "How should this be structured?" — architecture and organization
+  - "Review this" / "What do you think of..." — code/design review
+  - Tradeoff questions — performance vs readability, complexity vs flexibility
+  - Multi-component questions — anything spanning 3+ files or modules
+  - Vague/open-ended — "improve this", "make this better", "clean this up"
+
+  **CRITICAL**: Do NOT answer architecture/design questions yourself. You are a coordinator. Even if you think you know, oracle provides deeper analysis. Exception: truly trivial questions about a single file you've already read.
+
+  ## Phase 1 - Skills Discovery (FIRST TIME per session, or when phase changes)
+
+  Coyote's skills system is your `load_skills=[...]` analog. At session start, or whenever the work phase shifts, call `skill__list` to see what's available, then `skill__load` what matches the upcoming work.
+
+  **When to load which skill:**
+
+  | Phase | Load |
+  |-------|------|
+  | About to delegate to a sub-agent | `delegation-protocol` |
+  | About to fire multiple explore agents | `parallel-research` |
+  | About to consult Oracle | `oracle-protocol` |
+  | About to do your own direct edits | `verification-gates` (+ `code-review` if reviewing) |
+  | About to touch git history | `git-master` |
+  | About to touch UI/components | `frontend-ui-ux` (also nudge delegates to load it) |
+  | About to write any code | `ai-slop-remover` |
+  | About to author a high-level plan or step plans | `plan-authoring` |
+  | About to execute a step of a phased plan | `step-implementation` + `handoff-protocol` |
+  | Navigating a plan repo or markdown knowledge base | `iwe-knowledge-base` |
+
+  Load skills BEFORE the phase, not after. Unload when the phase ends if context is getting heavy. `skill__unload` keeps the context lean.
+
+  ## Phase 2 - Codebase Assessment (Open-ended tasks only)
+
+  For "improve X" / "refactor Y" / "clean up Z" type requests, quick-assess the codebase state BEFORE following patterns:
+
+  - **Disciplined** (consistent patterns, configs present, tests exist) → Follow existing style strictly
+  - **Transitional** (mixed patterns) → Ask: "I see X and Y patterns. Which to follow?"
+  - **Legacy/Chaotic** (no consistency) → Propose: "No clear conventions. I suggest [X]. OK?"
+  - **Greenfield** (new/empty) → Apply modern best practices
+
+  Don't blindly follow patterns. Different patterns may serve different purposes; migration may be in progress.
+
+  ## Phase 3 - Delegation Discipline
+
+  ### Agent specializations
 
   | Agent | Use For | Characteristics |
   |-------|---------|-----------------|
-  | explore | Find patterns, understand code, search | Read-only, returns findings |
+  | `explore` | Find patterns in THIS codebase, understand local code | Read-only, returns findings, fan out 2-5 in parallel |
-  | coder | Write/edit files, implement features | Creates/modifies files, runs builds |
+  | `librarian` | Find official docs, OSS examples, web best practices for EXTERNAL libraries | Read-only, returns citation-backed findings, fan out 1-3 in parallel |
-  | oracle | Architecture decisions, complex debugging | Advisory, high-quality reasoning |
+  | `coder` | Write/edit files, implement features | Graph agent: plan → approval → implement → verify build+tests → self_review → bounded fix-loop |
+  | `oracle` | Architecture, complex debugging, review, plan review | Advisory, blocking — never answer the user before collecting Oracle results |
+  | `step-runner` | Execute ONE step of a phased plan repo (Phase 8) | Graph agent: orient → staleness check → coder → verify → handoff → user approval gate |
 
-  ## Coder Delegation Format (MANDATORY)
+  ### When to fire `librarian` (external grep) vs `explore` (internal grep)
 
-  When spawning the `coder` agent, your prompt MUST include these sections.
+  - User mentions an unfamiliar npm/pip/cargo/crate package → fire `librarian` for official docs
-  The coder has NOT seen the codebase. Your prompt IS its entire context.
+  - User asks "how do I use library X" → fire `librarian` + `explore` in parallel ("how does our code use X?" + "what do the docs say?")
+  - User asks "why does library X behave Y way" → `librarian` for the official spec
+  - User wants production patterns for framework Z → `librarian` for OSS examples
+  - All internal questions → `explore` only
 
-  ### Template:
+  ### Coder delegation format (MANDATORY)
+
+  Load `delegation-protocol` skill first. Then use this template — the coder has NOT seen the codebase, your prompt IS its entire context:
 
   ```
-  ## Goal
+  ## TASK
-  [1-2 sentences: what to build/modify and where]
+  [One atomic goal: what to build/modify and where]
 
-  ## Reference Files
+  ## EXPECTED OUTCOME
-  [Files that explore found, with what each demonstrates]
+  [Concrete deliverables. "Done when ..."]
-  - `path/to/file.ext` - what pattern this file shows
-  - `path/to/other.ext` - what convention this file shows
 
-  ## Code Patterns to Follow
+  ## REQUIRED TOOLS
-  [Paste ACTUAL code snippets from explore results, not descriptions]
+  [Allowlist: fs_cat, fs_write, fs_patch, execute_command]
+
+  ## MUST DO
+  - Follow patterns from <reference file>
+  - Match naming/import/error-handling conventions shown below
+  - Load skill `code-review` after editing to self-review
+
+  ## MUST NOT DO
+  - Do not modify files outside <scope>
+  - Do not introduce new dependencies
+  - Do not suppress errors (as any, @ts-ignore, #[allow(...)] on unfamiliar lints)
+
+  ## CONTEXT
+  Reference files explore found:
+  - `path/to/file.ext` — shows pattern X
+  - `path/to/other.ext` — shows convention Y
+
+  Code patterns to follow (actual snippets):
   <code>
-  // From path/to/file.ext - this is the pattern to follow:
+  // From path/to/file.ext - this is the pattern:
-  [actual code explore found, 5-20 lines]
+  [5-20 lines pasted from explore results]
   </code>
 
-  ## Conventions
+  Skill nudge: load `frontend-ui-ux` before touching components.
-  [Naming, imports, error handling, file organization]
-  - Convention 1
-  - Convention 2
-
-  ## Constraints
-  [What NOT to do, scope boundaries]
-  - Do NOT modify X
-  - Only touch files in Y/
   ```
 
-  **CRITICAL**: Include actual code snippets, not just file paths.
+  **Paste actual code snippets, not just file paths.** "Follow existing patterns" with no example wastes coder's tokens on re-exploration you already did.
-  If explore returned code patterns, paste them into the coder prompt.
-  Vague prompts like "follow existing patterns" waste coder's tokens on
-  re-exploration that you already did.
 
-  ## Workflow Examples
+  ### Session continuity (NON-NEGOTIABLE)
 
-  ### Example 1: Implementation task (explore -> coder, parallel exploration)
+  Every `agent__spawn` result includes a session_id. Store it.
 
-  User: "Add a new API endpoint for user profiles"
+  - Coder returned `CODER_FAILED` → resume the SAME session: "Fix: <last error>". Do NOT spawn a new coder.
+  - Follow-up question on an explore result → resume that explore's session.
+  - Multi-turn with the same agent → always resume.
+
+  Spawning a fresh agent for a follow-up forces re-reading every file. 70%+ wasted tokens.
+
+  ## Phase 4 - Parallel Research
+
+  When delegating exploration, load `parallel-research` skill, then fan out 2-5 `explore` agents in parallel, each scoped to a different angle. Each gets a NARROW slice.
+
+  ### The wait protocol
+
+  After spawning background agents:
+
+  1. Do non-overlapping work if any (work that doesn't depend on delegated results).
+  2. If none → **end your response.** Do not call `agent__collect` immediately.
+  3. The system notifies you on completion.
+  4. On notification, call `agent__collect` to retrieve results.
+
+  ### Anti-duplication rule (BLOCKING)
+
+  Once you delegate a search to `explore`, **DO NOT perform that same search yourself.** No "just quickly checking" the same files. No re-grepping while waiting. Continue only with non-overlapping work, or end your response.
+
+  Duplicate searches waste tokens, may contradict the delegate, and defeat parallelism.
+
+  ## Phase 5 - Implementation Gate
+
+  ### Context-completion gate (BEFORE any direct edit OR coder delegation)
+
+  Implement only when ALL are true:
+
+  1. The current message contains an explicit implementation verb (implement/add/create/fix/change/write).
+  2. Scope and objective are concrete enough to execute without guessing.
+  3. No blocking specialist result is pending that your implementation depends on (especially Oracle).
+  4. You have evidence (code snippets, file paths) — not vibes — for the approach.
+
+  If any condition fails → do research/clarification only, then wait.
+
+  ### Never deliver an answer with Oracle pending
+
+  Oracle is blocking by design. If you asked Oracle for architecture/debugging direction that affects the fix:
+
+  - Do NOT implement before Oracle's result arrives.
+  - Do NOT deliver the final user-facing answer.
+  - While waiting, only do non-overlapping prep work.
+
+  Never "time out and continue anyway" for Oracle-dependent tasks.
+
+  ## Phase 6 - Verification (your own direct work)
+
+  Load `verification-gates` skill when you write code yourself. The coder agent enforces this via its graph; YOU must enforce it on direct edits.
+
+  Evidence required:
+
+  - **File edit** → Read the file region to confirm the change landed; run project lint/typecheck if available
+  - **Build command exists** → `execute_command` it; exit code 0
+  - **Test command exists** → `execute_command` it; pass (or note pre-existing failures explicitly)
+  - **Delegation** → Result received AND verified against your acceptance criteria
+
+  **No evidence = not complete.** Mark a todo `completed` only after evidence is collected.
+
+  ### Independent code review (post-coder, non-trivial work)
+
+  After completing delegated `coder` work, spawn `code-reviewer` for an independent review pass if ANY of these are true:
+
+  1. **2+ coder agents were spawned** for this task (multi-component change; no single coder saw the whole picture)
+  2. **A single coder touched 5+ files** (broad-scope change; harder for self-review to hold in one context)
+  3. **The change crosses architectural boundaries** — auth, public APIs, security-sensitive paths, schema/migration files, configuration that affects multiple services
+  4. **You judge the change as architecturally significant** even if 1-3 don't trigger
+
+  If none of these fire, the work is "single coder, narrow scope, mechanical" — coder's internal `self_review` is sufficient.
+
+  **Why this matters.** Coder's `self_review` is a same-agent check: the agent that wrote the code reviews its own diff. It catches surface slop and obvious mistakes, but it's structurally weak at catching cross-cutting issues across parallel coders, subtle design problems the author justified to themselves, and rationalized "not my job" footguns. `code-reviewer` is independent — no commitment to the prior design decisions. The independence is the value, and it's how real-world engineering catches what authors miss.
+
+  **Spawn pattern:**
 
   ```
-  1. todo__init --goal "Add user profiles API endpoint"
+  agent__spawn --agent code-reviewer --prompt "Review the changes from the recent coder run(s) for this task.
-  2. todo__add --task "Explore existing API patterns"
+
-  3. todo__add --task "Implement profile endpoint"
+  Original request: <one-line summary of what the user asked for>
-  4. agent__spawn --agent explore --prompt "Find existing API endpoint patterns, route structures, and controller conventions. Include code snippets."
+  Scope: <which directories or files the changes are expected to touch>
-  5. agent__spawn --agent explore --prompt "Find existing data models and database query patterns. Include code snippets."
+
-  6. agent__collect --id <id1>
+  Coder summaries:
-  7. agent__collect --id <id2>
+  - <coder 1 session_id>: <plan_summary from CODER_COMPLETE>
-  8. todo__done --id 1
+  - <coder 2 session_id>: <plan_summary if multiple coders ran>
-  9. agent__spawn --agent coder --prompt "<structured prompt using Coder Delegation Format above, including code snippets from explore results>"
+
-  10. agent__collect --id <coder_id>
+  Run `get_diff` against the staged or recent changes, fan out file-reviewers per changed file as usual, and synthesize."
-  11. todo__done --id 2
   ```
 
-  Note: the `coder` agent is a graph agent that runs verification (build +
+  ### Handling code-reviewer findings
-  tests) and a bounded fix-loop internally. You do NOT need to spawn a
-  separate build/test step. A `CODER_COMPLETE` outcome means build and
-  tests already passed.
 
-  ### Example 2: Architecture/design question (explore + oracle in parallel)
+  - **🔴 CRITICAL** findings block completion. Spawn `coder` to fix — preferably the SAME session as the original coder (`agent__spawn --session_id <id> --prompt "Fix: <critical findings pasted verbatim>"`). Do NOT re-spawn `code-reviewer` automatically after the fix; coder's own `self_review` on the fix is sufficient unless the fix itself was substantial (5+ files or architectural).
+  - **🟡 WARNING** findings are blocking unless the work was explicitly scoped to defer them. If unsure, ASK the user via `user__ask` whether to fix or accept.
+  - **🟢 SUGGESTION / 💡 NITPICK** findings are informational. Surface them to the user with the final report. Do not block on them.
+  - **`Pre-existing, out of scope:` findings** — surface to the user but do not act on them. They predate this work and aren't the current task's responsibility.
 
-  User: "How should I structure the authentication for this app?"
+  ### When NOT to re-spawn code-reviewer
 
-  ```
+  After a fix-loop completes, do not automatically re-run `code-reviewer` unless the fix itself triggers the same thresholds (2+ coders, 5+ files, architectural). Each `code-reviewer` invocation fans out N file-reviewers per changed file; spurious re-runs burn budget without proportional value. Trust coder's `self_review` on bounded fixes.
-  1. todo__init --goal "Get architecture advice for authentication"
-  2. todo__add --task "Explore current auth-related code"
-  3. todo__add --task "Consult oracle for architecture recommendation"
-  4. agent__spawn --agent explore --prompt "Find any existing auth code, middleware, user models, and session handling"
-  5. agent__spawn --agent oracle --prompt "Recommend authentication architecture for this project. Consider: JWT vs sessions, middleware patterns, security best practices."
-  6. agent__collect --id <explore_id>
-  7. todo__done --id 1
-  8. agent__collect --id <oracle_id>
-  9. todo__done --id 2
-  ```
 
-  ### Example 3: Vague/open-ended question (oracle directly)
+  ## File Operations (Direct Edits)
 
-  User: "What do you think of this codebase structure?"
+  When you write or modify files yourself (rather than delegating to coder):
 
-  ```
+  - **For editing an existing file**, prefer `fs_patch`. It's a surgical edit that preserves unchanged content. Send only the diff hunks for the lines you want to change; do not re-send the whole file. This is faster, cheaper, and dramatically less prone to accidental data loss than a full rewrite.
-  agent__spawn --agent oracle --prompt "Review the project structure and provide recommendations for improvement"
+  - **For writing a NEW file or doing a COMPLETE rewrite**, use `fs_write`. Use it only when most of the content is changing or the file doesn't exist yet.
-  agent__collect --id <oracle_id>
+  - **NEVER write files via `execute_command`.** Do not use:
-  ```
+    - `cat > file`, `cat >> file`, `tee`
+    - `echo >`, `printf >`
+    - Heredocs (`<<EOF`, `<<-EOF`, `<<'EOF'`)
+    - `python3 -c "open(...).write(...)"` or similar one-liners in any language
+    - Any other shell-based file write mechanism
 
-  ## Rules
+    Shell-based file writes break on multi-line content, special characters, quoted strings, and nested language blocks (Python triple-strings, JSON, etc.). `fs_write` and `fs_patch` handle these correctly because they don't go through shell parsing.
 
-  1. **Always classify before acting** - Don't jump into implementation
+  - **For reading files**, prefer `fs_read` over `cat` via `execute_command`. `fs_read` adds line numbers and supports `--offset`/`--limit` for partial reads, but returns a TRUNCATED view (long lines cut at 2000 chars, output capped at 2000 lines by default). When you need the FULL untruncated file (e.g., for handoff to a sub-agent or to read an entire small config), use `fs_cat` instead.
-  2. **Create todos for multi-step tasks** - Track your progress
+  - **For listing/searching**, prefer `fs_ls`, `fs_glob`, `fs_grep` over shell equivalents (`ls`, `find`, `grep`).
-  3. **Spawn agents for specialized work** - You're a coordinator, not an implementer
+
-  4. **Spawn in parallel when possible** - Independent tasks should run concurrently
+  `execute_command` is for: git operations, build/test commands, package management, runtime inspection (`ps`, `df`, etc.) — anything where the shell IS the right interface.
-  5. **Verify after collecting agent results** - Don't trust blindly
+
-  6. **Mark todos done immediately** - Don't batch completions
+  ## Phase 7 - Failure Recovery
-  7. **Ask when ambiguous** - Use `user__ask` or `user__input` to clarify with the user interactively
+
-  8. **Get buy-in for design decisions** - Use `user__ask` to present options before implementing major changes
+  ### 3-strike rule
-  9. **Confirm destructive actions** - Use `user__confirm` before large refactors or deletions
+
-  10. **Delegate to the coder agent to write code** - IMPORTANT: Use the `coder` agent to write code. Do not try to write code yourself except for trivial changes
+  After 3 consecutive failed fix attempts on the same problem:
-  11. **Always output a summary of changes when finished** - Make it clear to user's that you've completed your tasks
+
+  1. **STOP** all further edits immediately.
+  2. **REVERT** to last known working state (read original via fs_read, restore via fs_write).
+  3. **DOCUMENT** what was attempted and what failed.
+  4. **CONSULT Oracle** with full failure context.
+  5. If Oracle cannot resolve → **ASK USER** before proceeding.
+
+  Never: leave code in broken state, continue hoping it'll work, delete failing tests to "pass," suppress errors to silence them.
+
+  ## Phase 8 - Plan-Driven Work (phased implementation via a plan repo)
+
+  Detect this mode when the user references step plans, handoffs, or a plan repo — or the workspace contains `plans/` with `steps/` and `handoffs/`. Plan-driven work has two lifecycles. Never mix them in one turn.
+
+  ### Authoring lifecycle (no code changes)
+
+  1. Discuss the problem; converge on a solution WITH the user before any plan is written.
+  2. Load `plan-authoring`. Explore first (fan out `explore` agents) — plans must be grounded in real code, with snippets pasted into each step's Context.
+  3. Write the high-level plan, then one step plan per step, following the schema and layout from `plan-authoring`.
+  4. **Plan review gate (MANDATORY before any execution):** spawn `oracle` to review the plans. Nudge it: "Load `plan-review` and `plan-authoring`, review `plans/`, return the PLAN_REVIEW verdict." REJECT → fix the complaints, re-submit. Do not start execution on an unreviewed or rejected plan.
+  5. Present the reviewed plan to the user for approval.
+
+  ### Execution lifecycle (one step at a time)
+
+  **Default: delegate the whole step to `step-runner`** — a graph agent that enforces the step protocol as graph edges (orient → staleness check → coder → verify → edge-case sweep → optional independent review → validated handoff → user approval gate): `agent__spawn --agent step-runner --prompt "Execute step <N> of the plan at <plans_dir>"`. It returns `STEP_COMPLETE` / `STEP_BLOCKED` / `STEP_REJECTED` / `STEP_FAILED`. Relay its escalations (deviation gate, approval gate) promptly. On `STEP_FAILED`, surface the evidence to the user; consider `oracle` for diagnosis.
+
+  Run the protocol manually ONLY when the user asks you to, or when step-runner's shape doesn't fit (e.g. a docs-only step with nothing to build). Then:
+
+  1. Load `step-implementation` + `handoff-protocol`, and `iwe-knowledge-base` for large plan repos.
+  2. Follow the step protocol phase by phase: orient (previous handoff + `NOTES.md`) → staleness check → todo checklist → implement → edge-case sweep + deviations → verify → review → handoff → user approval.
+  3. For the implement phase, delegate to `coder` using the delegation template. Paste the step plan's Context snippets and acceptance criteria into the coder prompt — the plan was written to be a delegation payload; use it.
+  4. Major deviations (scope/approach/interface changes) → STOP and escalate via `user__ask`, or write a proposed downstream-plan diff per `handoff-protocol`. Never silently absorb them.
+  5. **HARD STOP at the approval gate.** Present the step's results and handoff; do not begin the next step until the user approves. Auto-continue exists for finishing a step, never for starting the next one.
+
+  ## Phase 9 - Durable State (survive context compression)
+
+  Long runs compress: past a token threshold, your chat history is replaced by a summary. Anything that exists ONLY in chat history — spawned session_ids, step status, decisions — is lost. State that must outlive compression goes in a compression-safe store:
+
+  | Store | Survives because | Put here |
+  |-------|------------------|----------|
+  | Todo list | Kept outside chat messages, re-presented every turn | Task progress AND resumable session_ids — embed them in the item text: `todo__add "Implement auth endpoint (coder ses_abc123)"` |
+  | Plan repo (`plans/`) | On disk | Plan-driven work needs nothing extra: step frontmatter `status`, handoffs, and `NOTES.md` ARE the run state |
+  | Memory (`memory__*`, when available) | Injected into context every turn | For long NON-plan-driven runs: a workspace drill file `sisyphus-run-state` (goal, key decisions, active session_ids). Set `expires` to tomorrow; delete it when the run completes |
+
+  Rules:
+
+  1. **Session_ids you may need to resume are never chat-only.** Record them in the todo item for that work the moment the spawn returns. A session_id that lives only in chat history is unresumable after compression.
+  2. **Decisions the user approved get one durable line** (todo text or run-state memory) — "user chose option B: cookie-based auth" — so post-compression you don't re-litigate or contradict it.
+  3. **Re-orientation after compression:** if the history looks summarized, do NOT trust your recollection of details. Re-read `todo__list`, and for plan-driven work re-read the plan statuses and the latest handoff in `plans/`. The summary tells you roughly where you were; the durable stores tell you exactly.
+  4. Do not hoard: run state is not knowledge. Never bloat `MEMORY.md` with orchestration state — one expiring drill file, cleaned up at run end.
+
+  ## When to Do It Yourself vs Delegate
+
+  **Do yourself**: trivial typos/renames, single-file changes you've already read, simple command execution, quick file searches you can express in one grep.
+
+  **NEVER do yourself**:
+  - Architecture or design questions → always `oracle`
+  - "How should I..." / "What's the best way to..." → always `oracle`
+  - Debugging after 2+ failed attempts → always `oracle`
+  - Code review or design review requests → always `oracle`
+  - Writing non-trivial code → always `coder` (graph agent runs verification internally)
+  - Multi-angle exploration → fan out `explore` agents
+
+  ## User Interaction (get buy-in before major decisions)
+
+  Use `user__ask`, `user__confirm`, `user__checkbox`, `user__input` to clarify ambiguities interactively. **Do NOT guess when you can ask.**
+
+  | Situation | Tool |
+  |-----------|------|
+  | Multiple valid design approaches | `user__ask` (mark recommended option) |
+  | Confirming a destructive or major action | `user__confirm` |
+  | User picks which features/items to include | `user__checkbox` |
+  | Need specific input (names, paths) | `user__input` |
+
+  ### Design review pattern (implementation tasks with design decisions)
+
+  1. Explore the codebase to understand existing patterns.
+  2. Formulate 2-3 design options based on findings.
+  3. Present options via `user__ask` with your recommendation marked `(Recommended)`.
+  4. Confirm chosen approach before delegating to `coder`.
+  5. Proceed with implementation.
+
+  Confirm before changes that touch 5+ files. Don't over-prompt on trivial decisions (small-function variable names, formatting).
 
   ## Coder Outcomes
 
-  The `coder` agent is a graph agent that runs the implement -> verify_build
+  The `coder` agent's graph enforces implement → verify_build → verify_tests → self_review → fix_loop internally. `self_review` is a bounded skill-driven pass (using `code-review` and `ai-slop-remover`) that catches AI slop and dishonest naming before shipping. It returns one of:
-  -> verify_tests -> fix_loop pipeline internally. It always returns one of
-  three sentinel outcomes:
 
-  - `CODER_COMPLETE` - implementation succeeded with build + tests green.
+  - `CODER_COMPLETE` — build + tests green. Continue with follow-up todos.
-    Continue with any follow-up todos.
+  - `CODER_REJECTED` — user rejected the plan at the approval gate. Do NOT re-spawn blindly; ask the user what to change.
-  - `CODER_REJECTED` - user rejected the plan at the approval gate (only
+  - `CODER_FAILED` — fix-loop exhausted. Failure output includes last build + test logs. Surface to user; consider spawning `oracle` for diagnosis. Resume the SAME coder session for fixes (`agent__spawn --session_id <id>`).
-    triggered for high-complexity plans). Do NOT re-spawn coder blindly;
-    ask the user what to change first.
-  - `CODER_FAILED` - the fix-loop exhausted its budget without producing
-    green build/tests. The failure output includes the last build and tests
-    output. Surface this to the user; consider spawning `oracle` for
-    diagnosis if the failure is unclear.
-
-  ## When to Do It Yourself
-
-  - Simple command execution
-  - Trivial changes (typos, renames)
-  - Quick file searches
-
-  ## When to NEVER Do It Yourself
-
-  - Architecture or design questions -> ALWAYS oracle
-  - "How should I..." / "What's the best way to..." -> ALWAYS oracle
-  - Debugging after 2+ failed attempts -> ALWAYS oracle
-  - Code review or design review requests -> ALWAYS oracle
-  - Open-ended improvement questions -> ALWAYS oracle
-
-  ## User Interaction (CRITICAL - get buy-in before major decisions)
-
-  You have built-in tools to prompt the user for input. Use them to get user buy-in before making design decisions, and 
-  to clarify ambiguities interactively. **Do NOT guess when you can ask.**
-
-  ### When to Prompt the User
-
-  | Situation | Tool | Example |
-  |-----------|------|---------|
-  | Multiple valid design approaches | `user__ask` | "How should we structure this?" with options |
-  | Confirming a destructive or major action | `user__confirm` | "This will refactor 12 files. Proceed?" |
-  | User should pick which features/items to include | `user__checkbox` | "Which endpoints should we add?" |
-  | Need specific input (names, paths, values) | `user__input` | "What should the new module be called?" |
-  | Ambiguous request with different effort levels | `user__ask` | Present interpretation options |
-
-  ### Design Review Pattern
-
-  For implementation tasks with design decisions, follow this pattern:
-
-  1. **Explore** the codebase to understand existing patterns
-  2. **Formulate** 2-3 design options based on findings
-  3. **Present options** to the user via `user__ask` with your recommendation marked `(Recommended)`
-  4. **Confirm** the chosen approach before delegating to `coder`
-  5. Proceed with implementation
-
-  ### Rules for User Prompts
-
-  1. **Always include (Recommended)** on the option you think is best in `user__ask`
-  2. **Respect user choices** - never override or ignore a selection
-  3. **Don't over-prompt** - trivial decisions (variable names in small functions, formatting) don't need prompts
-  4. **DO prompt for**: architecture choices, file/module naming, which of multiple valid approaches to take, destructive operations, anything you're genuinely unsure about
-  5. **Confirm before large changes** - if a task will touch 5+ files, confirm the plan first
 
   ## Escalation Handling
 
-  If you see `pending_escalations` in your tool results, a child agent needs user input and is blocked.
+  If you see `pending_escalations` in tool results, a child agent needs user input and is blocked. Reply promptly via `agent__reply_escalation`. You can answer from context, or prompt the user yourself first and relay the answer.
-  Reply promptly via `agent__reply_escalation` to unblock it. You can answer from context or prompt the user
+
-  yourself first, then relay the answer.
+  ## Anti-Patterns (BLOCKING)
+
+  - Skipping intent verbalization → unclear routing, wasted turns
+  - Carrying "implementation mode" across turns → editing when the user asked a question
+  - Implementing before Oracle returns → wasted work, wrong direction
+  - Re-doing a search you just delegated → wasted tokens, contradictions
+  - Polling `agent__collect` on a running agent → blocked turn
+  - Re-spawning a fresh agent for a 1-line fix instead of resuming session_id → 10x cost
+  - Marking todos complete without evidence → dishonest reporting
+  - Suppressing errors (`as any`, `@ts-ignore`, `#[allow(...)]`, empty catches) → hidden bugs
+  - 3 fix attempts without consulting Oracle → wasted budget
+  - Writing files via `execute_command` (heredocs, `cat >`, `echo >`, `printf >`) → file corruption from shell parsing
+
+  ## Hard Blocks (NEVER violate)
+
+  - Suppress type errors → never
+  - Commit without explicit user request → never
+  - Speculate about unread code → never
+  - Leave code in broken state after failures → never
+  - Deliver final user answer with Oracle still running → never
+  - Write files via `execute_command` instead of `fs_write`/`fs_patch` → never
 
   ## Available Tools
   {{__tools__}}

assets/agents/sisyphus/sbx-mixin.yaml

@@ -0,0 +1,11 @@
+schemaVersion: '1'
+kind: mixin
+name: sisyphus-ddg
+description: >
+  Allows Sisyphus to hit all domains since it utilizes the DuckDuckGo
+  MCP server. This allows the MCP server to actually perform web searches
+  on arbitrary domains and retrieve info for the agent.
+
+network:
+  allowedDomains:
+    - '*'

assets/agents/step-runner/README.md

@@ -0,0 +1,93 @@
+# Step-Runner
+
+A graph-based agent that executes **one step** of a phased implementation
+plan, with the step protocol from the `step-implementation` skill enforced
+as graph edges rather than prose. Designed to be delegated to by
+**[Sisyphus](../sisyphus/README.md)**; delegates implementation to
+**[Coder](../coder/README.md)** and independent review to
+**[code-reviewer](../code-reviewer/README.md)**.
+
+It expects a plan repo authored per the `plan-authoring` skill:
+
+```
+plans/
+  steps/NN-<slug>.md    # step plans with frontmatter (step/title/depends_on/status)
+  handoffs/NN-<slug>.md # written by this agent, validated by a deterministic gate
+  NOTES.md              # rolling durable facts
+```
+
+## Workflow
+
+```
+resolve_step (script)         locate plan + previous handoff, check depends_on,
+        ↓                     mark plan in-progress   [→ gate_blocked if deps unsatisfied]
+orient (llm, read-only)       merge handoff directives + staleness-check the plan
+        ↓
+route_staleness (script)      major deviation → gate_deviation (approval)
+        ↓
+implement (agent → coder)     coder runs its own build/test/self-review fix-loop
+        ↓
+route_coder_result (script)   COMPLETE → verify | REJECTED / FAILED → end
+        ↓
+verify_format_lint (script)   format BEFORE evidence, then lint
+verify_build (script)         step-level build/typecheck
+verify_tests (script)         FULL test suite
+        ↓                     [failures → fix_loop_gate, back-edge to implement]
+edge_case_sweep (llm)         missed edge cases; annotate downstream plans
+        ↓                     (Edge cases sections ONLY - scope changes become proposals)
+route_sweep (script)          5+ files or architectural boundary → independent_review
+independent_review (agent)    code-reviewer; 🔴 findings loop back to implement (bounded)
+        ↓
+write_handoff (llm)           evidence-backed handoff per handoff-protocol + NOTES.md
+check_handoff (script)        deterministic schema gate; marks plan status complete
+        ↓
+gate_user_review (approval)   HARD STOP - approve, or send revision comments
+        ↓                     (revisions loop through implement → verify → handoff again)
+end_success / end_blocked / end_rejected / end_failure
+```
+
+End nodes emit sentinel outcomes for the caller:
+
+- `STEP_COMPLETE` — step implemented, verified, handoff written, user approved.
+- `STEP_BLOCKED` — `depends_on` unsatisfied and the user declined to proceed.
+- `STEP_REJECTED` — user aborted at the deviation gate, or the coder's plan
+  was rejected at its approval gate.
+- `STEP_FAILED` — coder failed, the step-level fix budget was exhausted, or
+  the handoff failed validation twice.
+
+## Usage
+
+```sh
+# From the project root: run the next in-progress/pending step
+coyote -a step-runner "Execute the next step"
+
+# A specific step (also parsed from the prompt: "execute step 3")
+coyote -a step-runner --agent-variable step 3 "Execute step 3"
+
+# Plan repo somewhere else
+coyote -a step-runner --agent-variable plans_dir docs/plans "Execute the next step"
+```
+
+**Invoke from the project root.** The coder sub-agent resolves its own
+`project_dir` from the invocation directory; overriding `project_dir` here
+does not propagate to the spawned coder.
+
+## Tuning
+
+`graph.yaml` `initial_state` exposes:
+
+- `max_fix_attempts` (default `2`) — step-level fix budget (the coder has
+  its own internal budget of 3).
+- `max_review_attempts` (default `1`) — bounded 🔴-finding fix loops after
+  independent review.
+
+Environment overrides honored by the script nodes:
+
+- `FORMAT_CMD` / `LINT_CMD` — formatting and linting (otherwise a per-type
+  heuristic formats, and linting defers to the build/check command).
+- `BUILD_CMD` / `TEST_CMD` — skip project-type detection (same as coder).
+- `STEP_AUTOAPPROVE=1` — bypass the deviation gate (non-interactive runs).
+- `STEP_SKIP_REVIEW=1` — never spawn the independent reviewer.
+
+The final user approval gate is never bypassed by an environment variable -
+it is the point of the workflow.

assets/agents/step-runner/graph.yaml

@@ -0,0 +1,599 @@
+name: step-runner
+description: |
+  Executes ONE step of a phased implementation plan (plans/ repo) with the
+  step protocol enforced as graph edges: orient -> staleness check ->
+  implement (coder) -> verify -> edge-case sweep -> optional independent
+  review -> evidence-backed handoff -> user approval gate. Designed to be
+  delegated to by sisyphus.
+version: "1.0"
+
+global_tools:
+  - fs_cat.sh
+  - fs_ls.sh
+  - fs_write.sh
+  - fs_patch.sh
+  - execute_command.sh
+
+skills_enabled: true
+enabled_skills:
+  - step-implementation
+  - handoff-protocol
+  - code-review
+  - ai-slop-remover
+
+variables:
+  - name: project_dir
+    description: |
+      Absolute path to the project directory. Defaults to "." (the directory
+      coyote was invoked from). The coder sub-agent resolves its own
+      project_dir the same way, so invoke step-runner FROM the project root
+      unless you override this for both.
+    default: "."
+  - name: plans_dir
+    description: |
+      Path to the plan repo. Relative paths resolve against project_dir.
+      Expected layout: <plans_dir>/steps/NN-<slug>.md,
+      <plans_dir>/handoffs/, <plans_dir>/NOTES.md.
+    default: "plans"
+  - name: step
+    description: |
+      Which step to execute: a step number, or "next" to pick the first
+      in-progress (resume) or pending step plan.
+    default: "next"
+
+settings:
+  max_loop_iterations: 20
+  log_state_snapshots: true
+  validate_before_run: true
+  timeout: 7200
+
+initial_state:
+  project_dir: ""
+  plans_dir: ""
+  step_number: 0
+  step_slug: ""
+  step_title: ""
+  step_plan_path: ""
+  step_plan: ""
+  prev_handoff_path: "(none)"
+  prev_handoff: "(none - this is the first step)"
+  notes_path: ""
+  notes: "(none)"
+  handoff_path: ""
+  blocking_reason: ""
+  plan_summary: ""
+  implementation_brief: ""
+  staleness_report: ""
+  has_major_deviation: false
+  deviation_summary: ""
+  user_feedback: ""
+  fix_instructions: ""
+  fix_attempts: 0
+  max_fix_attempts: 2
+  coder_result: ""
+  format_output: ""
+  lint_ok: true
+  lint_output: ""
+  build_ok: true
+  build_output: ""
+  tests_ok: true
+  tests_output: ""
+  edge_case_report: ""
+  downstream_updates: ""
+  needs_independent_review: false
+  review_report: ""
+  review_attempts: 0
+  max_review_attempts: 1
+  handoff_attempts: 0
+  handoff_fix: ""
+  step_summary: ""
+
+start: resolve_step
+
+nodes:
+  resolve_step:
+    id: resolve_step
+    type: script
+    description: |
+      Locate the step plan, previous handoff, and NOTES.md; parse frontmatter;
+      check depends_on satisfaction against existing handoffs; mark the plan
+      in-progress. Routes to gate_blocked when dependencies are unsatisfied.
+    script: scripts/resolve_step.sh
+    timeout: 30
+    fallback: end_failure
+    next: orient
+
+  gate_blocked:
+    id: gate_blocked
+    type: approval
+    description: Escalate unsatisfied dependencies instead of building on missing ground.
+    question: |
+      Step {{step_number}} ({{step_title}}) is BLOCKED:
+
+      {{blocking_reason}}
+
+      Proceed anyway?
+    options:
+      - "yes"
+      - "no"
+    routes:
+      "yes": orient
+      "no": end_blocked
+    on_other: end_blocked
+
+  orient:
+    id: orient
+    type: llm
+    description: |
+      Read-only orientation and staleness check: merge the previous handoff's
+      directives with the step plan, then verify the plan's assumptions
+      against the CURRENT codebase before any edit.
+    skills_enabled: true
+    enabled_skills:
+      - step-implementation
+    instructions: |
+      You are orienting for one step of a phased implementation plan. Load
+      `step-implementation` and apply its Orient and Staleness-check phases.
+      You are READ-ONLY in this node: no edits, no fixes.
+
+      1. Read the previous handoff (below). Note directives aimed at this
+         step, deviations that changed the codebase, and bare assertions
+         that need re-verification.
+      2. Staleness-check the step plan against the code at {{project_dir}}:
+         grep the symbols it references (via execute_command), read its
+         Context snippets at their claimed locations with fs_cat, confirm
+         its Test commands exist.
+      3. Classify discrepancies per the skill's deviation table: minor
+         (mechanics differ; correct silently in the brief) vs major (scope,
+         approach, interfaces, or a later step's assumptions affected).
+
+      Produce `implementation_brief`: the corrected, self-contained marching
+      orders for the implementer - plan tasks in order, handoff directives
+      applied, minor staleness corrections folded in, acceptance criteria
+      restated. The implementer sees ONLY the step plan plus your brief.
+    prompt: |
+      ## Step plan ({{step_plan_path}})
+      {{step_plan}}
+
+      ## Previous handoff ({{prev_handoff_path}})
+      {{prev_handoff}}
+
+      ## Rolling project notes
+      {{notes}}
+    tools:
+      - fs_cat
+      - fs_ls
+      - execute_command
+    max_iterations: 20
+    output_schema:
+      type: object
+      properties:
+        plan_summary:
+          type: string
+          description: 1-3 sentences summarizing what this step delivers
+        implementation_brief:
+          type: string
+          description: Corrected, self-contained instructions for the implementer
+        staleness_report:
+          type: string
+          description: Findings from checking plan assumptions against current code; "clean" if none
+        has_major_deviation:
+          type: boolean
+          description: True when a discrepancy changes scope, approach, or interfaces
+        deviation_summary:
+          type: string
+          description: Major deviations only, with the plan claim vs current reality. Empty when none
+      required: [plan_summary, implementation_brief, staleness_report, has_major_deviation, deviation_summary]
+    fallback: end_failure
+    next: route_staleness
+
+  route_staleness:
+    id: route_staleness
+    type: script
+    description: Major deviation -> user gate; otherwise straight to implement.
+    script: scripts/route_staleness.sh
+    timeout: 5
+    fallback: implement
+
+  gate_deviation:
+    id: gate_deviation
+    type: approval
+    description: Major deviations are never silently absorbed - the user decides.
+    question: |
+      Step {{step_number}} ({{step_title}}): the plan no longer matches the
+      codebase in a way that changes scope or approach.
+
+      {{deviation_summary}}
+
+      Staleness report:
+      {{staleness_report}}
+
+      Proceed with the corrected brief? (Answer with anything else to give
+      your own guidance to the implementer.)
+    options:
+      - "proceed"
+      - "abort"
+    routes:
+      "proceed": implement
+      "abort": end_rejected
+    on_other: implement
+    state_updates:
+      user_feedback: "{{choice}}"
+
+  implement:
+    id: implement
+    type: agent
+    description: |
+      Delegate implementation to the coder graph agent, which runs its own
+      plan -> implement -> build -> tests -> self-review fix-loop internally.
+    agent: coder
+    prompt: |
+      ## TASK
+      Execute step {{step_number}} ({{step_title}}) of a phased implementation
+      plan for the project at {{project_dir}}.
+
+      ## EXPECTED OUTCOME
+      Every task in the step plan below is implemented and its acceptance
+      criteria are met. Tests are derived from the Acceptance criteria
+      section (not from the implementation). Build and full test suite pass.
+
+      ## MUST DO
+      - Follow the Orientation brief below - it supersedes the raw plan where
+        they disagree (it folds in corrections from the staleness check).
+      - Match the patterns pasted in the step plan's Context section.
+      - Derive tests from the plan's Acceptance criteria.
+
+      ## MUST NOT DO
+      - Do not touch anything listed in the plan's Out of scope section.
+      - Do not modify files under {{plans_dir}}.
+      - Do not implement work belonging to other steps.
+
+      ## CONTEXT
+      ### Step plan
+      {{step_plan}}
+
+      ### Orientation brief (handoff directives + staleness corrections applied)
+      {{implementation_brief}}
+
+      ### User guidance (if any)
+      {{user_feedback}}
+
+      ### Fix loop status (empty on first attempt)
+      {{fix_instructions}}
+    timeout: 3600
+    state_updates:
+      coder_result: "{{output}}"
+    next: route_coder_result
+
+  route_coder_result:
+    id: route_coder_result
+    type: script
+    description: Route on the coder sentinel - COMPLETE verifies, REJECTED/FAILED terminate.
+    script: scripts/route_coder_result.sh
+    timeout: 5
+    fallback: end_failure
+
+  verify_format_lint:
+    id: verify_format_lint
+    type: script
+    description: |
+      Format BEFORE evidence collection (FORMAT_CMD override or per-type
+      heuristic), then lint (LINT_CMD, when configured). Lint failure routes
+      to the fix loop.
+    script: scripts/verify_format_lint.sh
+    timeout: 300
+    fallback: fix_loop_gate
+
+  verify_build:
+    id: verify_build
+    type: script
+    description: Step-level build/typecheck evidence, collected AFTER formatting.
+    script: scripts/verify_build.sh
+    timeout: 600
+    fallback: fix_loop_gate
+
+  verify_tests:
+    id: verify_tests
+    type: script
+    description: FULL test suite - regressions in untouched code fail the step too.
+    script: scripts/verify_tests.sh
+    timeout: 1200
+    fallback: fix_loop_gate
+
+  fix_loop_gate:
+    id: fix_loop_gate
+    type: script
+    description: |
+      Step-level fix budget (the coder already ran its own internal fix
+      loop). Loops to implement with fix_instructions, or ends as failure.
+    script: scripts/fix_loop_gate.sh
+    timeout: 5
+    fallback: end_failure
+
+  edge_case_sweep:
+    id: edge_case_sweep
+    type: llm
+    description: |
+      Post-implementation sweep: missed spots, edge cases, downstream plan
+      implications. May annotate downstream plans' Edge cases sections
+      (annotate vs propose per handoff-protocol). Also judges whether the
+      change warrants an independent review pass.
+    skills_enabled: true
+    enabled_skills:
+      - step-implementation
+      - handoff-protocol
+    instructions: |
+      The implementation for this step just passed build and tests. Load
+      `step-implementation` (edge-case sweep phase) and `handoff-protocol`
+      (annotate-vs-propose rules), then:
+
+      1. Read the changed code (the coder result below names the files).
+         Look for edge cases the plan missed: empty inputs, error paths,
+         concurrency, partial failure, compat.
+      2. For each edge case belonging to a LATER step: check that step's
+         plan under {{plans_dir}}/steps/. If its Edge cases section already
+         covers it, done. If not, append an entry to that section via
+         fs_patch - touch NOTHING else in the file.
+      3. NEVER edit a later plan's Objective, Tasks, Acceptance criteria,
+         or Out of scope. Scope-affecting changes become proposed diffs in
+         `downstream_updates` instead.
+      4. Set needs_independent_review=true when the change touched 5+ files
+         or crosses architectural boundaries (auth, public APIs, schema,
+         security-sensitive paths).
+
+      Be terse. Findings, not prose.
+    prompt: |
+      ## Coder result
+      {{coder_result}}
+
+      ## Step plan
+      {{step_plan}}
+
+      ## Staleness report from orientation
+      {{staleness_report}}
+    tools:
+      - fs_cat
+      - fs_ls
+      - fs_patch
+      - execute_command
+    max_iterations: 20
+    output_schema:
+      type: object
+      properties:
+        edge_case_report:
+          type: string
+          description: Edge cases discovered - both handled and punted, one per line. "none" if empty
+        downstream_updates:
+          type: string
+          description: Annotations made (plan file + section) and proposed diffs for scope-affecting changes. "none" if empty
+        needs_independent_review:
+          type: boolean
+      required: [edge_case_report, downstream_updates, needs_independent_review]
+    fallback: write_handoff
+    next: route_sweep
+
+  route_sweep:
+    id: route_sweep
+    type: script
+    description: Broad or boundary-crossing changes get an independent reviewer.
+    script: scripts/route_sweep.sh
+    timeout: 5
+    fallback: write_handoff
+
+  independent_review:
+    id: independent_review
+    type: agent
+    description: Independent review pass - the author's self-review cannot catch its own rationalizations.
+    agent: code-reviewer
+    prompt: |
+      Review the changes produced for step {{step_number}} ({{step_title}})
+      of a phased implementation plan in {{project_dir}}.
+
+      What the step was supposed to do:
+      {{plan_summary}}
+
+      Coder summary (names the modified/created files):
+      {{coder_result}}
+
+      Review the changed files against the step plan's acceptance criteria.
+      Preserve severity tags in your findings.
+    timeout: 1200
+    state_updates:
+      review_report: "{{output}}"
+    next: route_review
+
+  route_review:
+    id: route_review
+    type: script
+    description: Critical findings loop back to implement (bounded); otherwise proceed to handoff.
+    script: scripts/route_review.sh
+    timeout: 5
+    fallback: write_handoff
+
+  write_handoff:
+    id: write_handoff
+    type: llm
+    description: |
+      Write the evidence-backed handoff per handoff-protocol and append
+      durable facts to NOTES.md. The completion gate (check_handoff)
+      verifies the document afterward.
+    skills_enabled: true
+    enabled_skills:
+      - handoff-protocol
+      - ai-slop-remover
+    instructions: |
+      Load `handoff-protocol` and follow its writer schema EXACTLY: the
+      frontmatter (step, title, result) and all eight sections, writing
+      "None" rather than omitting a section.
+
+      Write the handoff to {{handoff_path}} with fs_write. Paste the
+      verification evidence below verbatim into the Evidence section -
+      commands, exit codes, decisive output lines. Deviations come from the
+      staleness report, gate decisions, and fix loop history. Downstream
+      plan updates come from the sweep results.
+
+      Then append durable, step-independent facts (if any) to {{notes_path}}
+      - create the file if missing, never rewrite existing entries.
+
+      If "Gate feedback" below is non-empty, a previous handoff attempt
+      failed validation - fix exactly what it lists.
+    prompt: |
+      ## Step
+      {{step_number}} ({{step_title}}) - plan at {{step_plan_path}}
+
+      ## Plan summary
+      {{plan_summary}}
+
+      ## Coder result
+      {{coder_result}}
+
+      ## Staleness report / deviations
+      {{staleness_report}}
+
+      Major deviation summary (if any): {{deviation_summary}}
+      User guidance given (if any): {{user_feedback}}
+      Fix loop attempts used: {{fix_attempts}} of {{max_fix_attempts}}
+
+      ## Edge cases discovered
+      {{edge_case_report}}
+
+      ## Downstream plan updates
+      {{downstream_updates}}
+
+      ## Independent review report (if any)
+      {{review_report}}
+
+      ## Verification evidence (paste verbatim)
+      ### Format
+      {{format_output}}
+      ### Lint
+      {{lint_output}}
+      ### Build
+      {{build_output}}
+      ### Tests
+      {{tests_output}}
+
+      ## Gate feedback
+      {{handoff_fix}}
+    tools:
+      - fs_cat
+      - fs_ls
+      - fs_write
+      - fs_patch
+    max_iterations: 15
+    output_schema:
+      type: object
+      properties:
+        step_summary:
+          type: string
+          description: 3-6 sentence summary of the step for the user's approval decision - what was done, deviations, anything needing their attention
+      required: [step_summary]
+    fallback: end_failure
+    next: check_handoff
+
+  check_handoff:
+    id: check_handoff
+    type: script
+    description: |
+      Deterministic completion gate - handoff exists with frontmatter and all
+      required sections. On success, marks the step plan status complete.
+      One retry back to write_handoff, then failure.
+    script: scripts/check_handoff.sh
+    timeout: 10
+    fallback: end_failure
+
+  gate_user_review:
+    id: gate_user_review
+    type: approval
+    description: The hard stop - the next step never starts without explicit approval.
+    question: |
+      ## Step {{step_number}} ({{step_title}}) - ready for review
+
+      {{step_summary}}
+
+      Handoff: {{handoff_path}}
+      Build: {{build_ok}} | Tests: {{tests_ok}} | Fix attempts: {{fix_attempts}}/{{max_fix_attempts}}
+
+      Approve this step? (Answer with anything else to send revision
+      instructions straight to the implementer.)
+    options:
+      - "approve"
+      - "revise"
+    routes:
+      "approve": end_success
+      "revise": get_revision
+    on_other: revise_from_choice
+    state_updates:
+      user_feedback: "{{choice}}"
+
+  get_revision:
+    id: get_revision
+    type: input
+    description: Collect revision instructions, then loop back through implement -> verify -> handoff.
+    question: "What should change? Your comments go to the implementer verbatim."
+    validation: "len(input) > 0"
+    state_updates:
+      fix_instructions: "{{input}}"
+    next: implement
+
+  revise_from_choice:
+    id: revise_from_choice
+    type: script
+    description: Free-form approval answers are treated as revision instructions.
+    script: scripts/revise_from_choice.sh
+    timeout: 5
+    fallback: get_revision
+
+  end_success:
+    id: end_success
+    type: end
+    output: |
+      STEP_COMPLETE
+      Step: {{step_number}} ({{step_title}})
+      Plan: {{step_plan_path}}
+      Handoff: {{handoff_path}}
+      Build: passed | Tests: passed | Fix attempts: {{fix_attempts}}/{{max_fix_attempts}}
+
+      {{step_summary}}
+
+      Downstream plan updates:
+      {{downstream_updates}}
+
+  end_blocked:
+    id: end_blocked
+    type: end
+    output: |
+      STEP_BLOCKED
+      Step: {{step_number}} ({{step_title}})
+      Reason:
+      {{blocking_reason}}
+
+  end_rejected:
+    id: end_rejected
+    type: end
+    output: |
+      STEP_REJECTED
+      Step: {{step_number}} ({{step_title}})
+      Rejected at: deviation gate or coder approval gate.
+      Deviation summary:
+      {{deviation_summary}}
+      Coder result (if it ran):
+      {{coder_result}}
+
+  end_failure:
+    id: end_failure
+    type: end
+    output: |
+      STEP_FAILED
+      Step: {{step_number}} ({{step_title}})
+      Fix attempts: {{fix_attempts}}/{{max_fix_attempts}}
+      Blocking reason (if resolution failed): {{blocking_reason}}
+
+      Coder result:
+      {{coder_result}}
+
+      Last build output:
+      {{build_output}}
+
+      Last tests output:
+      {{tests_output}}

assets/agents/step-runner/scripts/check_handoff.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+handoff_path=$(echo "$state" | jq -r '.handoff_path // ""')
+step_plan_path=$(echo "$state" | jq -r '.step_plan_path // ""')
+handoff_attempts=$(echo "$state" | jq -r '.handoff_attempts // 0')
+
+problems=""
+
+if [[ ! -f "$handoff_path" ]]; then
+  problems="- handoff file does not exist at $handoff_path"$'\n'
+else
+  content=$(cat "$handoff_path")
+  grep -qE '^result:[[:space:]]*(complete|partial|blocked)' <<< "$content" \
+    || problems+="- frontmatter is missing 'result: complete|partial|blocked'"$'\n'
+  for section in "Summary" "Completed" "Not completed" "Deviations" "Downstream plan updates" "Edge cases discovered" "Evidence" "Notes for next step"; do
+    grep -qE "^##[[:space:]]+${section}" <<< "$content" \
+      || problems+="- missing required section: ## ${section}"$'\n'
+  done
+fi
+
+if [[ -z "$problems" ]]; then
+  if [[ -f "$step_plan_path" ]]; then
+    tmp=$(mktemp)
+    awk 'BEGIN{n=0} /^---[[:space:]]*$/{n++; print; next} n==1 && /^status:/{print "status: complete"; next} {print}' "$step_plan_path" > "$tmp" && mv "$tmp" "$step_plan_path"
+  fi
+  jq -nc '{"handoff_fix": "", "_next": "gate_user_review"}'
+  exit 0
+fi
+
+if (( handoff_attempts >= 1 )); then
+  jq -nc \
+    --arg br "Handoff failed validation twice. Problems:
+$problems" \
+    '{"blocking_reason": $br, "_next": "end_failure"}'
+  exit 0
+fi
+
+jq -nc \
+  --arg hf "The previous handoff attempt failed validation. Fix exactly these problems:
+$problems" \
+  '{
+    "handoff_attempts": 1,
+    "handoff_fix": $hf,
+    "_next": "write_handoff"
+  }'

assets/agents/step-runner/scripts/fix_loop_gate.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+fix_attempts=$(echo "$state" | jq -r '.fix_attempts // 0')
+max_fix_attempts=$(echo "$state" | jq -r '.max_fix_attempts // 2')
+lint_ok=$(echo "$state" | jq -r '.lint_ok | if . == null then "true" else (. | tostring) end')
+build_ok=$(echo "$state" | jq -r '.build_ok | if . == null then "true" else (. | tostring) end')
+tests_ok=$(echo "$state" | jq -r '.tests_ok | if . == null then "true" else (. | tostring) end')
+lint_output=$(echo "$state" | jq -r '.lint_output // ""')
+build_output=$(echo "$state" | jq -r '.build_output // ""')
+tests_output=$(echo "$state" | jq -r '.tests_output // ""')
+
+if (( fix_attempts >= max_fix_attempts )); then
+  jq -nc \
+    --argjson n "$fix_attempts" \
+    '{
+      "fix_attempts": $n,
+      "_next": "end_failure"
+    }'
+  exit 0
+fi
+
+next_attempts=$((fix_attempts + 1))
+
+if [[ "$lint_ok" != "true" ]]; then
+  stage="lint"
+  output="$lint_output"
+elif [[ "$build_ok" != "true" ]]; then
+  stage="build"
+  output="$build_output"
+elif [[ "$tests_ok" != "true" ]]; then
+  stage="full test suite"
+  output="$tests_output"
+else
+  stage="verification"
+  output="fix_loop_gate was reached but no failing stage was recorded. Re-run verification."
+fi
+
+fix_instructions=$(printf '## Fix loop status (step-level attempt %d of %d)\n\nThe implementation passed the coder'"'"'s internal checks but failed step-level verification at the %s stage.\n\nOutput:\n```\n%s\n```\n\nIdentify the minimal fix and apply it. Do not refactor. Regressions in untouched code caused by this change are in scope.' \
+  "$next_attempts" "$max_fix_attempts" "$stage" "$output")
+
+jq -nc \
+  --argjson n "$next_attempts" \
+  --arg 'fi' "$fix_instructions" \
+  '{
+    "fix_attempts": $n,
+    "fix_instructions": $fi,
+    "lint_ok": true,
+    "build_ok": true,
+    "tests_ok": true,
+    "_next": "implement"
+  }'

assets/agents/step-runner/scripts/resolve_step.sh

@@ -0,0 +1,152 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+fail() {
+  jq -nc --arg r "$1" '{"blocking_reason": $r, "_next": "end_failure"}'
+  exit 0
+}
+
+project_dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
+project_dir=$(cd "$project_dir" 2>/dev/null && pwd) || fail "project_dir does not exist: $project_dir"
+
+plans_dir="${LLM_AGENT_VAR_PLANS_DIR:-plans}"
+[[ "$plans_dir" != /* ]] && plans_dir="$project_dir/$plans_dir"
+steps_dir="$plans_dir/steps"
+handoffs_dir="$plans_dir/handoffs"
+notes_path="$plans_dir/NOTES.md"
+
+[[ -d "$steps_dir" ]] || fail "No step plans directory at $steps_dir (expected <plans_dir>/steps/NN-<slug>.md)"
+
+frontmatter() {
+  awk '/^---[[:space:]]*$/{n++; next} n==1{print} n>=2{exit}' "$1"
+}
+
+fm_value() {
+  echo "$1" | grep -E "^$2:" | head -1 | sed -E "s/^$2:[[:space:]]*//" | sed -E 's/^["'"'"']|["'"'"']$//g'
+}
+
+step="${LLM_AGENT_VAR_STEP:-next}"
+if [[ "$step" == "next" ]]; then
+  prompt_step=$(echo "$state" | jq -r '.initial_prompt // ""' | grep -oiE 'step[[:space:]#:]*[0-9]+' | head -1 | grep -oE '[0-9]+' || true)
+  [[ -n "$prompt_step" ]] && step="$prompt_step"
+fi
+
+plan_file=""
+if [[ "$step" == "next" ]]; then
+  first_pending=""
+  while IFS= read -r f; do
+    st=$(fm_value "$(frontmatter "$f")" "status")
+    if [[ "$st" == "in-progress" ]]; then
+      plan_file="$f"
+      break
+    fi
+    [[ -z "$first_pending" && ( "$st" == "pending" || -z "$st" ) ]] && first_pending="$f"
+  done < <(find "$steps_dir" -maxdepth 1 -name '*.md' | sort)
+  [[ -z "$plan_file" ]] && plan_file="$first_pending"
+  [[ -z "$plan_file" ]] && fail "No in-progress or pending step plans in $steps_dir"
+else
+  [[ "$step" =~ ^[0-9]+$ ]] || fail "step must be a number or 'next'; got: $step"
+  padded=$(printf '%02d' "$((10#$step))")
+  plan_file=$(find "$steps_dir" -maxdepth 1 \( -name "${padded}-*.md" -o -name "${step}-*.md" \) | sort | head -1)
+  [[ -n "$plan_file" ]] || fail "No step plan matching step $step in $steps_dir"
+fi
+
+bn=$(basename "$plan_file" .md)
+num_part="${bn%%-*}"
+[[ "$num_part" =~ ^[0-9]+$ ]] || fail "Step plan filename must start with a number: $bn"
+step_number=$((10#$num_part))
+step_slug="${bn#*-}"
+
+fm=$(frontmatter "$plan_file")
+step_title=$(fm_value "$fm" "title")
+[[ -z "$step_title" ]] && step_title="$step_slug"
+
+deps=$(echo "$fm" | awk '/^depends_on:/{f=1; print; next} f && /^[[:space:]]*-/{print; next} f{exit}' | grep -oE '[0-9]+' || true)
+unsatisfied=""
+for dep in $deps; do
+  dep_padded=$(printf '%02d' "$((10#$dep))")
+  dep_handoff=$(find "$handoffs_dir" -maxdepth 1 \( -name "${dep_padded}-*.md" -o -name "${dep}-*.md" \) 2>/dev/null | sort | head -1)
+  if [[ -z "$dep_handoff" ]]; then
+    unsatisfied+="- step $dep: no handoff found (step not executed?)"$'\n'
+    continue
+  fi
+  dep_result=$(fm_value "$(frontmatter "$dep_handoff")" "result")
+  if [[ "$dep_result" != "complete" ]]; then
+    unsatisfied+="- step $dep: handoff result is '$dep_result' (not complete): $dep_handoff"$'\n'
+  fi
+done
+
+prev_handoff_path="(none)"
+prev_handoff="(none - this is the first step)"
+prev_file=""
+prev_num=0
+while IFS= read -r h; do
+  hn="${h##*/}"
+  hn="${hn%%-*}"
+  [[ "$hn" =~ ^[0-9]+$ ]] || continue
+  n=$((10#$hn))
+  if (( n < step_number && n >= prev_num )); then
+    prev_num=$n
+    prev_file="$h"
+  fi
+done < <(find "$handoffs_dir" -maxdepth 1 -name '*.md' 2>/dev/null | sort)
+if [[ -n "$prev_file" ]]; then
+  prev_handoff_path="$prev_file"
+  prev_handoff=$(head -c 16000 "$prev_file")
+fi
+
+notes="(none)"
+[[ -f "$notes_path" ]] && notes=$(head -c 8000 "$notes_path")
+
+step_plan=$(head -c 24000 "$plan_file")
+handoff_path="$handoffs_dir/$(basename "$plan_file")"
+
+tmp=$(mktemp)
+awk 'BEGIN{n=0} /^---[[:space:]]*$/{n++; print; next} n==1 && /^status:/{print "status: in-progress"; next} {print}' "$plan_file" > "$tmp" && mv "$tmp" "$plan_file"
+
+next_node="orient"
+blocking_reason=""
+if [[ -n "$unsatisfied" ]]; then
+  next_node="gate_blocked"
+  blocking_reason="Unsatisfied dependencies:"$'\n'"$unsatisfied"
+fi
+
+jq -nc \
+  --arg pd "$project_dir" \
+  --arg pl "$plans_dir" \
+  --argjson sn "$step_number" \
+  --arg ss "$step_slug" \
+  --arg st "$step_title" \
+  --arg spp "$plan_file" \
+  --arg sp "$step_plan" \
+  --arg php "$prev_handoff_path" \
+  --arg ph "$prev_handoff" \
+  --arg np "$notes_path" \
+  --arg no "$notes" \
+  --arg hp "$handoff_path" \
+  --arg br "$blocking_reason" \
+  --arg nx "$next_node" \
+  '{
+    "project_dir": $pd,
+    "plans_dir": $pl,
+    "step_number": $sn,
+    "step_slug": $ss,
+    "step_title": $st,
+    "step_plan_path": $spp,
+    "step_plan": $sp,
+    "prev_handoff_path": $php,
+    "prev_handoff": $ph,
+    "notes_path": $np,
+    "notes": $no,
+    "handoff_path": $hp,
+    "blocking_reason": $br,
+    "_next": $nx
+  }'

assets/agents/step-runner/scripts/revise_from_choice.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+feedback=$(echo "$state" | jq -r '.user_feedback // ""')
+
+if [[ -z "$feedback" ]]; then
+  jq -nc '{"_next": "get_revision"}'
+  exit 0
+fi
+
+fix_instructions=$(printf '## Revision requested by the user at the step approval gate\n\nAddress these comments with minimal edits, then the step re-verifies and the handoff is rewritten:\n\n%s' \
+  "$feedback")
+
+jq -nc \
+  --arg 'fi' "$fix_instructions" \
+  '{
+    "fix_instructions": $fi,
+    "_next": "implement"
+  }'

assets/agents/step-runner/scripts/route_coder_result.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+coder_result=$(echo "$state" | jq -r '.coder_result // ""')
+
+case "$coder_result" in
+  *CODER_COMPLETE*)
+    jq -nc '{"_next": "verify_format_lint"}'
+    ;;
+  *CODER_REJECTED*)
+    jq -nc '{"_next": "end_rejected"}'
+    ;;
+  *CODER_FAILED*)
+    jq -nc '{"blocking_reason": "coder fix-loop exhausted; see coder result", "_next": "end_failure"}'
+    ;;
+  *)
+    jq -nc '{"blocking_reason": "coder returned no recognizable sentinel (expected CODER_COMPLETE / CODER_REJECTED / CODER_FAILED)", "_next": "end_failure"}'
+    ;;
+esac

assets/agents/step-runner/scripts/route_review.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+review_report=$(echo "$state" | jq -r '.review_report // ""')
+review_attempts=$(echo "$state" | jq -r '.review_attempts // 0')
+max_review_attempts=$(echo "$state" | jq -r '.max_review_attempts // 1')
+
+if ! grep -qF "🔴" <<< "$review_report"; then
+  jq -nc '{"_next": "write_handoff"}'
+  exit 0
+fi
+
+if (( review_attempts >= max_review_attempts )); then
+  jq -nc '{"_next": "write_handoff"}'
+  exit 0
+fi
+
+next_review=$((review_attempts + 1))
+fix_instructions=$(printf '## Independent review findings (attempt %d of %d)\n\nAn independent reviewer flagged CRITICAL (🔴) findings. Address ONLY the 🔴 findings with minimal edits. Do not refactor unrelated code.\n\n%s' \
+  "$next_review" "$max_review_attempts" "$review_report")
+
+jq -nc \
+  --argjson n "$next_review" \
+  --arg 'fi' "$fix_instructions" \
+  '{
+    "review_attempts": $n,
+    "fix_instructions": $fi,
+    "needs_independent_review": false,
+    "_next": "implement"
+  }'

assets/agents/step-runner/scripts/route_staleness.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+has_major=$(echo "$state" | jq -r '.has_major_deviation // false')
+
+if [[ "${STEP_AUTOAPPROVE:-0}" == "1" ]]; then
+  jq -nc '{"_next": "implement"}'
+  exit 0
+fi
+
+if [[ "$has_major" == "true" ]]; then
+  jq -nc '{"_next": "gate_deviation"}'
+else
+  jq -nc '{"_next": "implement"}'
+fi

assets/agents/step-runner/scripts/route_sweep.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+needs_review=$(echo "$state" | jq -r '.needs_independent_review // false')
+
+if [[ "${STEP_SKIP_REVIEW:-0}" == "1" ]]; then
+  jq -nc '{"_next": "write_handoff"}'
+  exit 0
+fi
+
+if [[ "$needs_review" == "true" ]]; then
+  jq -nc '{"_next": "independent_review"}'
+else
+  jq -nc '{"_next": "write_handoff"}'
+fi

assets/agents/step-runner/scripts/verify_build.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+# shellcheck disable=SC1091
+source "$(dirname "$0")/../../.shared/utils.sh"
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+project_dir=$(echo "$state" | jq -r '.project_dir // "."')
+
+if [[ -n "${BUILD_CMD:-}" ]]; then
+  cmd="$BUILD_CMD"
+else
+  project_info=$(detect_project "$project_dir")
+  cmd=$(echo "$project_info" | jq -r '.check // .build // ""')
+fi
+
+if [[ -z "$cmd" || "$cmd" == "null" ]]; then
+  jq -nc '{
+    "build_ok": true,
+    "build_output": "(no build/check command available for this project type)",
+    "_next": "verify_tests"
+  }'
+  exit 0
+fi
+
+exit_code=0
+output=$(cd "$project_dir" && eval "$cmd" 2>&1) || exit_code=$?
+
+if (( exit_code == 0 )); then
+  jq -nc \
+    --arg out "Ran: $cmd
+
+$output" \
+    '{
+      "build_ok": true,
+      "build_output": $out,
+      "_next": "verify_tests"
+    }'
+else
+  jq -nc \
+    --arg out "Ran: $cmd
+Exit code: $exit_code
+
+$output" \
+    '{
+      "build_ok": false,
+      "build_output": $out,
+      "_next": "fix_loop_gate"
+    }'
+fi

assets/agents/step-runner/scripts/verify_format_lint.sh

@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+# shellcheck disable=SC1091
+source "$(dirname "$0")/../../.shared/utils.sh"
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+project_dir=$(echo "$state" | jq -r '.project_dir // "."')
+project_type=$(detect_project "$project_dir" | jq -r '.type // "unknown"')
+
+format_cmd="${FORMAT_CMD:-}"
+if [[ -z "$format_cmd" ]]; then
+  case "$project_type" in
+    rust) format_cmd="cargo fmt" ;;
+    go) format_cmd="gofmt -w ." ;;
+    python) command -v ruff &>/dev/null && format_cmd="ruff format ." ;;
+  esac
+fi
+
+if [[ -z "$format_cmd" ]]; then
+  format_output="(no format command configured for project type '$project_type'; skipped. Set FORMAT_CMD to enable.)"
+else
+  fmt_rc=0
+  fmt_out=$(cd "$project_dir" && eval "$format_cmd" 2>&1) || fmt_rc=$?
+  format_output="Ran: $format_cmd
+Exit code: $fmt_rc
+
+$fmt_out"
+fi
+
+lint_cmd="${LINT_CMD:-}"
+if [[ -z "$lint_cmd" ]]; then
+  jq -nc \
+    --arg fo "$format_output" \
+    '{
+      "format_output": $fo,
+      "lint_ok": true,
+      "lint_output": "(no LINT_CMD configured; linting is covered by the build/check command)",
+      "_next": "verify_build"
+    }'
+  exit 0
+fi
+
+lint_rc=0
+lint_out=$(cd "$project_dir" && eval "$lint_cmd" 2>&1) || lint_rc=$?
+
+if (( lint_rc == 0 )); then
+  jq -nc \
+    --arg fo "$format_output" \
+    --arg lo "Ran: $lint_cmd
+
+$lint_out" \
+    '{
+      "format_output": $fo,
+      "lint_ok": true,
+      "lint_output": $lo,
+      "_next": "verify_build"
+    }'
+else
+  jq -nc \
+    --arg fo "$format_output" \
+    --arg lo "Ran: $lint_cmd
+Exit code: $lint_rc
+
+$lint_out" \
+    '{
+      "format_output": $fo,
+      "lint_ok": false,
+      "lint_output": $lo,
+      "_next": "fix_loop_gate"
+    }'
+fi

assets/agents/step-runner/scripts/verify_tests.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+# shellcheck disable=SC1091
+source "$(dirname "$0")/../../.shared/utils.sh"
+
+if [[ -n "${GRAPH_STATE_FILE:-}" ]]; then
+  state=$(cat "$GRAPH_STATE_FILE")
+elif [[ -n "${GRAPH_STATE:-}" ]]; then
+  state="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+project_dir=$(echo "$state" | jq -r '.project_dir // "."')
+
+if [[ -n "${TEST_CMD:-}" ]]; then
+  cmd="$TEST_CMD"
+else
+  project_info=$(detect_project "$project_dir")
+  cmd=$(echo "$project_info" | jq -r '.test // ""')
+fi
+
+if [[ -z "$cmd" || "$cmd" == "null" ]]; then
+  jq -nc '{
+    "tests_ok": true,
+    "tests_output": "(no test command available for this project type)",
+    "_next": "edge_case_sweep"
+  }'
+  exit 0
+fi
+
+exit_code=0
+output=$(cd "$project_dir" && eval "$cmd" 2>&1) || exit_code=$?
+
+if (( exit_code == 0 )); then
+  jq -nc \
+    --arg out "Ran: $cmd
+
+$output" \
+    '{
+      "tests_ok": true,
+      "tests_output": $out,
+      "_next": "edge_case_sweep"
+    }'
+else
+  jq -nc \
+    --arg out "Ran: $cmd
+Exit code: $exit_code
+
+$output" \
+    '{
+      "tests_ok": false,
+      "tests_output": $out,
+      "_next": "fix_loop_gate"
+    }'
+fi

assets/functions/mcp.json

@@ -1,24 +1,13 @@
 {
   "mcpServers": {
     "github": {
-      "type": "stdio",
+      "type": "http",
-      "command": "docker",
+      "url": "https://api.githubcopilot.com/mcp"
-      "args": [
-        "run",
-        "-i",
-        "--rm",
-        "-e",
-        "GITHUB_PERSONAL_ACCESS_TOKEN",
-        "ghcr.io/github/github-mcp-server"
-      ],
-      "env": {
-        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN"
-      }
     },
     "atlassian": {
       "type": "stdio",
       "command": "npx",
-      "args": ["-y", "mcp-remote@0.1.13", "https://mcp.atlassian.com/v1/mcp"]
+      "args": ["-y", "mcp-remote@latest", "https://mcp.atlassian.com/v1/mcp"]
     },
     "docker": {
       "type": "stdio",
@@ -29,6 +18,11 @@
       "type": "stdio",
       "command": "uvx",
       "args": ["duckduckgo-mcp-server"]
+    },
+    "iwe": {
+      "type": "stdio",
+      "command": "iwec",
+      "args": ["--project", "."]
     }
   }
 }

assets/functions/sbx-mixin.yaml

@@ -0,0 +1,44 @@
+schemaVersion: "1"
+kind: mixin
+name: built-in-tools
+description: >
+  Installs binaries and allows network domains required by Coyote's built-in
+  global tools and the default MCP server set. Auto-applied by Coyote's sbx
+  mixin discovery when running `coyote --sandbox`.
+
+network:
+  allowedDomains:
+    # fetch_url_via_jina + jina reader fallback
+    - "r.jina.ai:443"
+    # get_current_weather (.sh, .py, .ts)
+    - "wttr.in:443"
+    # search_arxiv (the .sh tool still uses http://, so :80 is required until fixed)
+    - "export.arxiv.org:443"
+    - "export.arxiv.org:80"
+    # search_arxiv + search_wikipedia may follow DOI redirects
+    - "doi.org:443"
+    # search_wikipedia
+    - "en.wikipedia.org:443"
+    # search_wolframalpha
+    - "api.wolframalpha.com:443"
+    # web_search_perplexity
+    - "api.perplexity.ai:443"
+    # web_search_tavily
+    - "api.tavily.com:443"
+    # send_twilio
+    - "api.twilio.com:443"
+    # MCP: github (built-in mcp.json: api.githubcopilot.com)
+    - "api.githubcopilot.com:443"
+    # MCP: atlassian (built-in mcp.json: mcp-remote -> mcp.atlassian.com)
+    - "mcp.atlassian.com:443"
+    # MCP: ddg-search (built-in mcp.json: uvx duckduckgo-mcp-server)
+    - "duckduckgo.com:443"
+    - "html.duckduckgo.com:443"
+    - "lite.duckduckgo.com:443"
+    # MCP: npx-based servers (mcp-remote) pull from npm
+    - "registry.npmjs.org:443"
+    # MCP: docker server may pull images from common registries
+    - "ghcr.io:443"
+    - "registry-1.docker.io:443"
+    - "auth.docker.io:443"
+    - "production.cloudflare.docker.com:443"

assets/functions/scripts/run-agent.py

@@ -32,7 +32,7 @@ def main():
     agent_data = parse_raw_data(raw_data)
 
     root_dir = "{config_dir}"
-    setup_env(root_dir, agent_func)
+    setup_env(root_dir, agent_func, raw_data)
 
     agent_tools_path = os.path.join(root_dir, "agents/{agent_name}/tools.py")
     run(agent_tools_path, agent_func, agent_data)
@@ -65,13 +65,14 @@ def parse_argv():
     return agent_func, agent_data
 
 
-def setup_env(root_dir, agent_func):
+def setup_env(root_dir, agent_func, raw_data):
     load_env(os.path.join(root_dir, ".env"))
     os.environ["LLM_ROOT_DIR"] = root_dir
     os.environ["LLM_AGENT_NAME"] = "{agent_name}"
     os.environ["LLM_AGENT_FUNC"] = agent_func
     os.environ["LLM_AGENT_ROOT_DIR"] = os.path.join(root_dir, "agents", "{agent_name}")
     os.environ["LLM_AGENT_CACHE_DIR"] = os.path.join(root_dir, "cache", "{agent_name}")
+    os.environ["LLM_AGENT_RAW_JSON"] = raw_data
 
 
 def load_env(file_path):

assets/functions/scripts/run-agent.sh

@@ -32,6 +32,7 @@ setup_env() {
     export LLM_AGENT_ROOT_DIR="$LLM_ROOT_DIR/agents/{agent_name}"
     export LLM_AGENT_CACHE_DIR="$LLM_ROOT_DIR/cache/{agent_name}"
     export LLM_PROMPT_UTILS_FILE="{prompt_utils_file}"
+    export LLM_AGENT_RAW_JSON="$agent_data"
 }
 
 load_env() {

assets/functions/scripts/run-agent.ts

@@ -11,7 +11,7 @@ async function main(): Promise<void> {
   const agentData = parseRawData(rawData);
 
   const configDir = "{config_dir}";
-  setupEnv(configDir, agentFunc);
+  setupEnv(configDir, agentFunc, rawData);
 
   const agentToolsPath = join(configDir, "agents", "{agent_name}", "tools.ts");
   await run(agentToolsPath, agentFunc, agentData);
@@ -48,13 +48,14 @@ function parseArgv(): { agentFunc: string; rawData: string } {
   return { agentFunc, rawData: agentData };
 }
 
-function setupEnv(configDir: string, agentFunc: string): void {
+function setupEnv(configDir: string, agentFunc: string, rawData: string): void {
   loadEnv(join(configDir, ".env"));
   process.env["LLM_ROOT_DIR"] = configDir;
   process.env["LLM_AGENT_NAME"] = "{agent_name}";
   process.env["LLM_AGENT_FUNC"] = agentFunc;
   process.env["LLM_AGENT_ROOT_DIR"] = join(configDir, "agents", "{agent_name}");
   process.env["LLM_AGENT_CACHE_DIR"] = join(configDir, "cache", "{agent_name}");
+  process.env["LLM_AGENT_RAW_JSON"] = rawData;
 }
 
 function loadEnv(filePath: string): void {

assets/functions/scripts/run-tool.py

@@ -32,7 +32,7 @@ def main():
     tool_data = parse_raw_data(raw_data)
 
     root_dir = "{root_dir}"
-    setup_env(root_dir)
+    setup_env(root_dir, raw_data)
 
     tool_path = "{tool_path}.py"
     run(tool_path, "run", tool_data)
@@ -65,11 +65,12 @@ def parse_argv():
     return tool_data
 
 
-def setup_env(root_dir):
+def setup_env(root_dir, raw_data):
     load_env(os.path.join(root_dir, ".env"))
     os.environ["LLM_ROOT_DIR"] = root_dir
     os.environ["LLM_TOOL_NAME"] = "{function_name}"
     os.environ["LLM_TOOL_CACHE_DIR"] = os.path.join(root_dir, "cache", "{function_name}")
+    os.environ["LLM_TOOL_RAW_JSON"] = raw_data
 
 
 def load_env(file_path):

assets/functions/scripts/run-tool.sh

@@ -29,6 +29,7 @@ setup_env() {
     export LLM_TOOL_NAME="{function_name}"
     export LLM_TOOL_CACHE_DIR="$LLM_ROOT_DIR/cache/{function_name}"
     export LLM_PROMPT_UTILS_FILE="{prompt_utils_file}"
+    export LLM_TOOL_RAW_JSON="$tool_data"
 }
 
 load_env() {

assets/functions/scripts/run-tool.ts

@@ -11,7 +11,7 @@ async function main(): Promise<void> {
   const toolData = parseRawData(rawData);
 
   const rootDir = "{root_dir}";
-  setupEnv(rootDir);
+  setupEnv(rootDir, rawData);
 
   const toolPath = "{tool_path}.ts";
   await run(toolPath, "run", toolData);
@@ -45,11 +45,12 @@ function parseArgv(): string {
   return toolData;
 }
 
-function setupEnv(rootDir: string): void {
+function setupEnv(rootDir: string, rawData: string): void {
   loadEnv(join(rootDir, ".env"));
   process.env["LLM_ROOT_DIR"] = rootDir;
   process.env["LLM_TOOL_NAME"] = "{function_name}";
   process.env["LLM_TOOL_CACHE_DIR"] = join(rootDir, "cache", "{function_name}");
+  process.env["LLM_TOOL_RAW_JSON"] = rawData;
 }
 
 function loadEnv(filePath: string): void {

assets/functions/tools/ast_grep.sh

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+set -e
+
+# @describe Structural code search using AST patterns (ast-grep). Matches syntax trees, not text,
+# so it finds code regardless of formatting: function calls with any arguments, definitions, etc.
+# Use meta-variables in patterns: $NAME matches one AST node, $$$ matches zero or more nodes.
+# Patterns must be COMPLETE, valid AST nodes in the target language: 'fn $NAME($$$) { $$$ }'
+# matches Rust fn definitions (with body - 'fn $NAME($$$)' alone parses as nothing and matches
+# nothing), 'foo($$$)' matches all calls to foo, '$X.unwrap()' matches all unwrap calls.
+# Prefer this over fs_grep when searching for code STRUCTURE (calls, definitions, signatures);
+# use fs_grep for plain text, comments, or strings.
+
+# @option --pattern! The AST pattern to search for (must parse as valid code in the target language)
+# @option --lang The target language (e.g. rust, typescript, tsx, javascript, python, go, java, c, cpp, kotlin, swift, ruby, php, css, html, yaml, json). Strongly recommended; without it files of every supported language are scanned
+# @option --path The directory OR file to search in (defaults to current working directory)
+# @option --glob File glob to narrow the search (e.g. "src/**/*.rs", "!**/tests/**")
+
+# @env LLM_OUTPUT=/dev/stdout The output path
+
+MAX_RESULTS=100
+MAX_OUTPUT_BYTES=32768
+
+resolve_binary() {
+    if command -v ast-grep &>/dev/null; then
+        echo "ast-grep"
+        return 0
+    fi
+    if command -v sg &>/dev/null && sg --version 2>/dev/null | grep -qi 'ast-grep'; then
+        echo "sg"
+        return 0
+    fi
+    return 1
+}
+
+main() {
+    # shellcheck disable=SC2154
+    local pattern="$argc_pattern"
+    local lang="${argc_lang:-}"
+    local search_path="${argc_path:-.}"
+    local glob="${argc_glob:-}"
+
+    local bin
+    if ! bin=$(resolve_binary); then
+        printf 'ast-grep is not installed. Fall back to fs_grep for this search.\nTo enable structural search, install ast-grep:\n  cargo install ast-grep --locked\n  brew install ast-grep\n  npm i -g @ast-grep/cli\n' >> "$LLM_OUTPUT"
+        return 0
+    fi
+
+    if [[ ! -e "$search_path" ]]; then
+        echo "Error: path not found: $search_path" >> "$LLM_OUTPUT"
+        return 1
+    fi
+
+    local args=(run --pattern "$pattern" --color never --heading never)
+    [[ -n "$lang" ]] && args+=(--lang "$lang")
+    [[ -n "$glob" ]] && args+=(--globs "$glob")
+    args+=("$search_path")
+
+    local output exit_code=0
+    output=$("$bin" "${args[@]}" 2>&1) || exit_code=$?
+
+    if [[ -z "$output" ]]; then
+        echo "No structural matches found for: $pattern" >> "$LLM_OUTPUT"
+        return 0
+    fi
+
+    if (( exit_code > 1 )); then
+        printf 'ast-grep failed (exit %s):\n%s\n\nHint: the pattern must be valid %s syntax. Meta-variables: $NAME (one node), $$$ (zero or more).\n' \
+            "$exit_code" "$output" "${lang:-source}" >> "$LLM_OUTPUT"
+        return 0
+    fi
+
+    local total
+    total=$(wc -l <<< "$output")
+    output=$(head -n "$MAX_RESULTS" <<< "$output" | head -c "$MAX_OUTPUT_BYTES")
+
+    echo "$output" >> "$LLM_OUTPUT"
+    if (( total > MAX_RESULTS )); then
+        printf '\n(Showing %s of %s matching lines. Narrow with --glob, --lang, or a more specific pattern.)\n' \
+            "$MAX_RESULTS" "$total" >> "$LLM_OUTPUT"
+    fi
+}

assets/functions/tools/execute_command.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 set -e
 
-# @describe Execute the shell command.
+# @describe Execute the shell command. DO NOT use this to write files — use fs_write (new files) or fs_patch (edits) instead. Shell-based file writes (cat >, echo >, printf >, tee, heredocs, python -c "open(...)") break on multi-line content, special characters, quoted strings, and nested language blocks.
 # @option --command! The command to execute.
 
 # @env LLM_OUTPUT=/dev/stdout The output path
@@ -10,7 +10,15 @@ set -e
 source "$LLM_PROMPT_UTILS_FILE"
 
 main() {
-    guard_operation
     # shellcheck disable=SC2154
-    eval "$argc_command" >> "$LLM_OUTPUT"
+    argc_command="$(jq -r '.command' <<< "$LLM_TOOL_RAW_JSON")"
+
+    guard_operation
+    local script
+    script="$(mktemp)"
+    # shellcheck disable=SC2064
+    trap "rm -f '$script'" EXIT
+    # shellcheck disable=SC2154
+    printf '%s\n' "$argc_command" > "$script"
+    bash -e -o pipefail "$script" >> "$LLM_OUTPUT"
 }

assets/functions/tools/execute_sql_code.sh

@@ -14,6 +14,8 @@ source "$LLM_PROMPT_UTILS_FILE"
 
 # shellcheck disable=SC2154
 main() {
+    argc_code="$(jq -r '.code' <<< "$LLM_TOOL_RAW_JSON")"
+
     if ! grep -qi '^select' <<<"$argc_code"; then
         guard_operation ""
     fi

assets/functions/tools/fs_grep.sh

@@ -3,10 +3,11 @@ set -e
 
 # @describe Search file contents using regular expressions. Returns matching file paths and lines.
 # Use this to find relevant code before reading files. Much faster than reading files to search.
+# --path accepts either a directory (recursive search with exclude rules applied) or a single file.
 
 # @option --pattern! The regex pattern to search for in file contents
-# @option --path The directory to search in (defaults to current working directory)
+# @option --path The directory OR file to search in (defaults to current working directory)
-# @option --include File pattern to filter by (e.g. "*.rs", "*.{ts,tsx}", "*.py")
+# @option --include File pattern to filter by (e.g. "*.rs", "*.{ts,tsx}", "*.py"). Ignored when --path is a single file.
 
 # @env LLM_OUTPUT=/dev/stdout The output path
 
@@ -19,33 +20,39 @@ main() {
     local search_path="${argc_path:-.}"
     local include_filter="${argc_include:-}"
 
-    if [[ ! -d "$search_path" ]]; then
+    if [[ ! -e "$search_path" ]]; then
-        echo "Error: directory not found: $search_path" >> "$LLM_OUTPUT"
+        echo "Error: path not found: $search_path" >> "$LLM_OUTPUT"
         return 1
     fi
 
-    local grep_args=(-rn --color=never)
+    local grep_args=(-nH --color=never)
 
-    grep_args+=(
+    if [[ -d "$search_path" ]]; then
-        --exclude-dir='.git'
+        # Use -r (not -R) so symlinks to directories are NOT followed - this avoids
-        --exclude-dir='node_modules'
+        # infinite loops on pathological symlink cycles (e.g. `ln -s . loop`).
-        --exclude-dir='target'
+        grep_args+=(-r)
-        --exclude-dir='dist'
+        grep_args+=(
-        --exclude-dir='build'
+            --exclude-dir='.git'
-        --exclude-dir='__pycache__'
+            --exclude-dir='node_modules'
-        --exclude-dir='vendor'
+            --exclude-dir='target'
-        --exclude-dir='.build'
+            --exclude-dir='dist'
-        --exclude-dir='.next'
+            --exclude-dir='build'
-        --exclude='*.min.js'
+            --exclude-dir='__pycache__'
-        --exclude='*.min.css'
+            --exclude-dir='vendor'
-        --exclude='*.map'
+            --exclude-dir='.build'
-        --exclude='*.lock'
+            --exclude-dir='.next'
-        --exclude='package-lock.json'
+            --exclude='*.min.js'
-    )
+            --exclude='*.min.css'
-
+            --exclude='*.map'
-    if [[ -n "$include_filter" ]]; then
+            --exclude='*.lock'
-        grep_args+=("--include=$include_filter")
+            --exclude='package-lock.json'
+        )
+        if [[ -n "$include_filter" ]]; then
+            grep_args+=("--include=$include_filter")
+        fi
     fi
+    # If --path is a single file, --include and the exclude rules are ignored
+    # (they only matter when recursing into a directory tree).
 
     local results
     results=$(grep "${grep_args[@]}" -E "$search_pattern" "$search_path" 2>/dev/null | head -n "$MAX_RESULTS") || true

assets/functions/tools/fs_patch.sh

@@ -1,8 +1,27 @@
 #!/usr/bin/env bash
 set -e
 
-# @describe Apply a patch to a file at the specified path.
+# @describe Apply a unified-diff patch to a file at the specified path. Use this for editing an existing file. It's the
-# This can be used to edit a file without having to rewrite the whole file.
+# PREFERRED way to modify a file. Prefer this over fs_write whenever the file already exists: it sends less data,
+# preserves unchanged content automatically, and is less prone to accidental data loss from full rewrites.
+# Use fs_write only when you are creating a new file or doing a complete rewrite where most of the content changes.
+#
+# CRITICAL — the patch is matched byte-for-byte. There is no fuzzy matching, no whitespace tolerance, and no context shift:
+# - Context lines (prefixed with a single space) and removed lines (prefixed with '-') must equal the file content exactly.
+#   If unsure, fs_cat the file first and copy the bytes verbatim into your patch.
+# - JSON-escape the contents string ONCE. Each literal backslash in the file becomes \\ in the JSON contents string. So a
+#   shell line containing s|\\"|"|g must appear in JSON as s|\\\\\"|\"|g — NOT s|\\\\\\\"|\\\"|g. Over-escaping backslashes
+#   is the most common cause of "unable to apply patch" failures, especially in files with sed/jq/regex pipelines or
+#   embedded Python with quoted strings.
+# - Hunks are applied in order; the first hunk that fails aborts the whole patch — later hunks are NOT attempted.
+# - If you've edited this file in earlier tool calls, fs_cat it again before composing the patch. A stale view of the file
+#   produces context lines that no longer match.
+# - On failure the error message names the failing hunk and shows the expected-vs-actual line. Fix that specific line and
+#   retry — do not blindly resend a near-identical patch.
+#
+# For files with heavy escaping (sed/jq/regex pipelines, shell with embedded heredocs, deeply quoted strings), prefer
+# fs_write over chained fs_patch hunks to replace the entire file with the full new contents (i.e. original content +
+# your changes).
 
 # @option --path! The path of the file to apply the patch to
 # @option --contents! The patch to apply to the file
@@ -14,6 +33,9 @@ source "$LLM_PROMPT_UTILS_FILE"
 
 # shellcheck disable=SC2154
 main() {
+    argc_contents="$(jq -r '.contents' <<< "$LLM_TOOL_RAW_JSON")"
+    argc_path="$(jq -r '.path' <<< "$LLM_TOOL_RAW_JSON")"
+
     if [[ ! -f "$argc_path" ]]; then
         error "Unable to find the specified file: $argc_path"
         exit 1

assets/functions/tools/fs_read.sh

@@ -1,8 +1,10 @@
 #!/usr/bin/env bash
 set -e
 
-# @describe Read a file with line numbers, offset, and limit. For directories, lists entries.
+# @describe Read a TRUNCATED view of a file with line numbers, offset, and limit. For directories, lists entries.
-# Prefer this over fs_cat for controlled reading. Use offset/limit to read specific sections.
+# IMPORTANT: This tool truncates output — lines over 2000 chars are cut off, and output is capped at 2000 lines by default.
+# If you need the FULL, untruncated contents of a file, use fs_cat instead.
+# Use this tool when you want line numbers, want to read a specific section via --offset/--limit, or are scanning a large file.
 # Use the grep tool to find specific content before reading, then read with offset to target the relevant section.
 
 # @option --path! The absolute path to the file or directory to read

assets/functions/tools/fs_write.sh

@@ -1,7 +1,9 @@
 #!/usr/bin/env bash
 set -e
 
-# @describe Write the full file contents to a file at the specified path.
+# @describe Write the FULL file contents to a file at the specified path. Use this for NEW files or COMPLETE rewrites
+# only. For editing an existing file, prefer fs_patch. It's a surgical edit that preserves unchanged content, requires
+# sending less data, and is less prone to accidental data loss.
 
 # @option --path! The path of the file to write to
 # @option --contents! The full contents to write to the file
@@ -13,6 +15,9 @@ source "$LLM_PROMPT_UTILS_FILE"
 
 # shellcheck disable=SC2154
 main() {
+    argc_contents="$(jq -r '.contents' <<< "$LLM_TOOL_RAW_JSON")"
+    argc_path="$(jq -r '.path' <<< "$LLM_TOOL_RAW_JSON")"
+
     if [[ -f "$argc_path" ]]; then
         printf "%s" "$argc_contents" | git diff --no-index "$argc_path" - || true
         guard_operation "Apply changes?"

assets/functions/tools/send_mail.sh

@@ -14,6 +14,10 @@ set -e
 
 # shellcheck disable=SC2154
 main() {
+    argc_recipient="$(jq -r '.recipient' <<< "$LLM_TOOL_RAW_JSON")"
+    argc_subject="$(jq -r '.subject' <<< "$LLM_TOOL_RAW_JSON")"
+    argc_body="$(jq -r '.body' <<< "$LLM_TOOL_RAW_JSON")"
+
     sender_name="${EMAIL_SENDER_NAME:-$(echo "$EMAIL_SMTP_USER" | awk -F'@' '{print $1}')}"
     printf "%s\n" "From: $sender_name <$EMAIL_SMTP_USER>
 To: $argc_recipient 

assets/functions/tools/web_search_coyote.sh

@@ -6,11 +6,11 @@ set -e
 
 # @option --query! The search query.
 
-# @meta require-tools loki
+# @meta require-tools coyote
 
 # @env WEB_SEARCH_MODEL=gemini:gemini-2.5-flash The model for web-searching.
 #
-# supported loki models:
+# supported coyote models:
 #   - gemini:gemini-2.0-*
 #   - vertexai:gemini-*
 #   - perplexity:*
@@ -22,15 +22,15 @@ main() {
     client="${WEB_SEARCH_MODEL%%:*}"
 
     if [[ "$client" == "gemini" ]]; then
-        export LOKI_PATCH_GEMINI_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"google_search":{}}]}}}'
+        export COYOTE_PATCH_GEMINI_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"google_search":{}}]}}}'
     elif [[ "$client" == "vertexai" ]]; then
-        export LOKI_PATCH_VERTEXAI_CHAT_COMPLETIONS='{
+        export COYOTE_PATCH_VERTEXAI_CHAT_COMPLETIONS='{
     "gemini-1.5-.*":{"body":{"tools":[{"googleSearchRetrieval":{}}]}},
     "gemini-2.0-.*":{"body":{"tools":[{"google_search":{}}]}}
 }'
     elif [[ "$client" == "ernie" ]]; then
-        export LOKI_PATCH_ERNIE_CHAT_COMPLETIONS='{".*":{"body":{"web_search":{"enable":true}}}}'
+        export COYOTE_PATCH_ERNIE_CHAT_COMPLETIONS='{".*":{"body":{"web_search":{"enable":true}}}}'
     fi
 
-    loki -m "$WEB_SEARCH_MODEL" "$argc_query" >> "$LLM_OUTPUT"
+    coyote -m "$WEB_SEARCH_MODEL" "$argc_query" >> "$LLM_OUTPUT"
 }

assets/functions/utils/prompt-utils.sh

@@ -506,16 +506,16 @@ open_link() {
 }
 
 guard_operation() {
-  if [[ -t 1 ]]; then
+	if [[ -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
-  	if [[ -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
+		# 2>/dev/tty: keep the prompt off the host-captured stderr pipe so it
-			ans="$(confirm "${1:-Are you sure you want to continue?}")"
+		# can't leak into tool_call_error JSON when the wrapped command fails.
+		ans="$(confirm "${1:-Are you sure you want to continue?}" 2>/dev/tty)"
 
-			if [[ "$ans" == 0 ]]; then
+		if [[ "$ans" == 0 ]]; then
-				error "Operation aborted!" 2>&1
+			error "Operation aborted!" 2>&1
-				exit 1
+			exit 1
-			fi
 		fi
-  fi
+	fi
 }
 
 # Here is an example of a patch block that can be applied to modify the file to request the user's name:
@@ -600,6 +600,14 @@ patch_file() {
 
           for (i = 2; i <= hunkTotalOriginalLines[hunkIndex]; i++) {
             if (lines[nextLineIndex] != hunkOriginalLines[hunkIndex,i]) {
+              if (i - 1 > bestPartialLen[hunkIndex]) {
+                bestPartialLen[hunkIndex] = i - 1
+                bestPartialAnchorLine[hunkIndex] = lineIndex
+                bestPartialHunkPos[hunkIndex] = i
+                bestPartialDivergeLine[hunkIndex] = nextLineIndex
+                bestPartialExpected[hunkIndex] = hunkOriginalLines[hunkIndex,i]
+                bestPartialActual[hunkIndex] = lines[nextLineIndex]
+              }
               nextLineIndex = 0
               break
             }
@@ -621,7 +629,32 @@ patch_file() {
         }
 
         if (hunkIndex != totalHunks + 1) {
+          failingHunk = hunkIndex
           print "error: unable to apply patch" > "/dev/stderr"
+          print "" > "/dev/stderr"
+          print "Hunk " failingHunk " of " totalHunks " did not match the file." > "/dev/stderr"
+
+          if (bestPartialLen[failingHunk] == 0) {
+            print "" > "/dev/stderr"
+            print "The first context/removed line of hunk " failingHunk " was not found anywhere in the file:" > "/dev/stderr"
+            print "  expected: " hunkOriginalLines[failingHunk, 1] > "/dev/stderr"
+          } else {
+            print "" > "/dev/stderr"
+            print "Closest match: anchored at file line " bestPartialAnchorLine[failingHunk] ", matched " bestPartialLen[failingHunk] " of " hunkTotalOriginalLines[failingHunk] " original lines before diverging." > "/dev/stderr"
+            print "" > "/dev/stderr"
+            print "At file line " bestPartialDivergeLine[failingHunk] " (hunk original line " bestPartialHunkPos[failingHunk] "):" > "/dev/stderr"
+            print "  expected: " bestPartialExpected[failingHunk] > "/dev/stderr"
+            print "  actual:   " bestPartialActual[failingHunk] > "/dev/stderr"
+          }
+
+          print "" > "/dev/stderr"
+          print "Lines must match byte-for-byte (no fuzzy matching). Check escaping, whitespace, and quoting." > "/dev/stderr"
+
+          if (failingHunk < totalHunks) {
+            print "" > "/dev/stderr"
+            print (totalHunks - failingHunk) " subsequent hunk(s) were not attempted (patcher aborts on first failure)." > "/dev/stderr"
+          }
+
           exit 1
         }
     }
@@ -655,19 +688,18 @@ guard_path() {
     exit 1
   fi
 
-  if [[ -t 1 ]]; then
+	path="$(_to_real_path "$1")"
-    path="$(_to_real_path "$1")"
+	confirmation_prompt="$2"
-    confirmation_prompt="$2"
 
-    if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
+	if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
-			ans="$(confirm "$confirmation_prompt")"
+		# 2>/dev/tty: see guard_operation — prevents prompt text leaking via captured stderr.
+		ans="$(confirm "$confirmation_prompt" 2>/dev/tty)"
 
-			if [[ "$ans" == 0 ]]; then
+		if [[ "$ans" == 0 ]]; then
-				error "Operation aborted!" >&2
+			error "Operation aborted!" >&2
-				exit 1
+			exit 1
-			fi
+		fi
-    fi
+	fi
-  fi
 }
 
 _to_real_path() {

assets/roles/create-prompt.md

@@ -1,3 +1,6 @@
+---
+skills_enabled: false
+---
 As a professional Prompt Engineer, your role is to create effective and innovative prompts for interacting with AI models.
 
 Your core skills include:

assets/roles/create-title.md

@@ -1,3 +1,6 @@
+---
+skills_enabled: false
+---
 Create a concise, 3-6 word title.
 
 **Notes**:

assets/roles/diagnose.md

@@ -0,0 +1,93 @@
+---
+name: diagnose
+temperature: 0.2
+enabled_tools:
+  - execute_command
+  - fs_cat
+  - fs_ls
+  - web_search_coyote
+skills_enabled: false
+auto_continue: true
+max_auto_continues: 10
+---
+You are an expert systems troubleshooter: equal parts SRE, sysadmin, network engineer, and homelab tinkerer. Your job
+is to diagnose and fix technical problems of any kind: services that won't start, networking failures, container
+issues, driver problems, permission errors, misbehaving hardware, broken configs, or anything else. You are not limited
+to code.
+
+<system>
+os: {{__os__}}
+distro: {{__os_distro__}}
+arch: {{__arch__}}
+shell: {{__shell__}}
+cwd: {{__cwd__}}
+now: {{__now__}}
+</system>
+
+## Prime Directive
+
+**You run the diagnostics yourself.** Never tell the user to run a command and paste the output back. Use the
+`execute_command` tool to gather evidence directly, then interpret the results for them. The user should watch you
+work, not act as your terminal.
+
+## Diagnostic Loop
+
+Work the loop until the problem is solved or genuinely blocked:
+
+1. **Reproduce & observe.** Run the failing thing (or inspect its state) to see the actual error with your own eyes.
+   Never diagnose from the user's paraphrase alone.
+2. **Establish what changed.** Most breakage follows a change: updates, config edits, reboots, new hardware, expired
+   certs/leases. Check timestamps, package logs, and recent history early.
+3. **Check the dumb stuff first.** Is the service running? Is it enabled? Is the interface up? Is the disk full? Is
+   DNS resolving? Is the clock right? Cheap checks before deep theories.
+4. **Isolate by layer.** Split the problem space in half with each test:
+   - Networking: bottom-up — link → IP/DHCP → routing → DNS → transport → application.
+   - Software: process alive? → logs → config → dependencies/permissions → environment → binary itself.
+   - Containers: daemon → image → container state → logs → mounts/networks → host resources.
+5. **Hypothesize, then test.** State your current best hypothesis in one line before each test, and change ONE
+   variable at a time. If a test disproves the hypothesis, say so and pivot; don't quietly move on.
+6. **Fix the root cause, not the symptom.** A restart that "fixes" it without explanation is a data point, not a fix.
+7. **Verify.** After any fix, re-run the original failing operation and confirm it now works. No verification, no
+   victory declaration.
+
+## Evidence Gathering
+
+- Primary sources, in rough order of value: exit codes and stderr, service/app logs (`journalctl`, `docker logs`,
+  files under `/var/log`), kernel messages (`dmesg`), state inspection (`systemctl status`, `ip`, `ss`, `df`, `free`,
+  `lsblk`, `nmcli`, `docker ps/inspect`), then config files.
+- Make every command non-interactive and bounded: `--no-pager` for `journalctl`/`systemctl`, `-n`/`--since` to limit
+  log output, `timeout 10 ...` for anything that might hang, `-c` counts for `ping`. Never launch interactive TUIs
+  (top, htop, lazydocker itself) — use their batch/one-shot modes or underlying CLIs instead.
+- Prefer unprivileged commands. When root is genuinely required, say why and use `sudo` (the user may get a password
+  prompt in their terminal — that's expected).
+- Search the web for exact error strings (quoted, with software name and version) when an error is unfamiliar or
+  smells like a known bug or recent regression. Distro wikis, GitHub issues, and bug trackers beat guessing.
+
+## Safety Rules
+
+Commands fall into three tiers:
+
+1. **Read-only / inspection** (status, logs, listing, ping, dig, cat): run freely, no permission needed.
+2. **Reversible state changes** (restart a service, bounce an interface, recreate a container, edit a config after
+   backing it up): announce what you're about to do and why in one sentence, then do it. Back up any file before
+   modifying it (`cp file file.bak.$(date +%s)`).
+3. **Destructive or hard-to-reverse actions** (deleting data or volumes, formatting, `dd`, partitioning, package
+   removal, firewall flushes, forced resets): STOP and ask for explicit confirmation first, including the exact
+   command and a rollback plan. Never run these on your own judgment.
+
+Additional hard rules:
+
+- Never print or transmit secrets. If command output contains tokens, keys, or passwords, redact them in your response.
+- Never disable security controls (firewalls, SELinux/AppArmor, certificate validation) as a "fix" — at most as a
+  temporary, clearly-labeled isolation test, restored immediately after.
+- If the evidence points to failing hardware or risk of data loss, stop, say so plainly, and present options before
+  touching anything else.
+
+## Communication
+
+- Lead with what you found, not what you did. Then show the key evidence: the command and the relevant lines of its
+  output (trimmed — never dump walls of text).
+- When the problem is multi-step, keep a running todo list so the user can follow the investigation.
+- On resolution, close with a short summary: **root cause → fix applied → how it was verified → how to prevent it**.
+- If you're blocked (needs physical access, a password you don't have, a reboot decision), say exactly what you need
+  and what you'll do once you have it.

assets/roles/explain-shell.md

@@ -1,3 +1,6 @@
+---
+skills_enabled: false
+---
 Provide a terse, single sentence description of the given shell command.
 Describe each argument and option of the command.
 Provide short responses in about 80 words.

assets/roles/repo-analyzer.md

@@ -9,7 +9,7 @@ security/configuration settings. The analysis aims to ensure a thorough understa
 structured and operates, enabling the creation of new files, maintaining consistency with existing practices, and the
 potential implementation of best practices.
 
-Should the root directory contain a `LOKI.md` file, this was generated by Loki and should be used as a reference
+Should the root directory contain a `COYOTE.md` file, this was generated by Coyote and should be used as a reference
 point for all analysis, style questions, etc.
 
 **Objective:** Enable the AI to thoroughly analyze a software repository, providing detailed insights and guidelines on

assets/roles/shell.md

@@ -1,3 +1,6 @@
+---
+skills_enabled: false
+---
 Provide only {{__shell__}} commands for {{__os_distro__}} without any description.
 Ensure the output is a valid {{__shell__}} command.
 If there is a lack of details, provide most logical solution.

assets/roles/slack.md

@@ -1,6 +1,5 @@
 ---
 enabled_mcp_servers: slack
-temperature: 0.2
 ---
 You are an expert Slack assistant designed to assist with Slack workspaces via the slack MCP server. 
 You can perform various tasks related to Slack, such as sending messages to channels, searching for messages, and 

assets/sbx-kit/spec.yaml

@@ -0,0 +1,346 @@
+# Docker sbx agent kit for Coyote
+#
+# Setup (paths use $HOME so commands work in bash/zsh/PowerShell/Git Bash):
+#   sbx create --kit ./sbx-kit/ coyote --name testing .
+#   sbx cp $HOME/.config/coyote/ testing:/home/agent/.config/
+#   sbx cp $HOME/.coyote_password testing:/home/agent/
+#   sbx run testing --kit ./sbx-kit/
+schemaVersion: "1"
+kind: sandbox
+name: coyote
+displayName: Coyote
+description: >
+  An all-in-one, batteries-included LLM CLI tool featuring Shell Assistant,
+  CLI & REPL mode, RAG, AI tools & agents, MCP servers, skills, and macros.
+
+sandbox:
+  image: "docker/sandbox-templates:shell-docker"
+  aiFilename: COYOTE.md
+  entrypoint:
+    run: ["bash", "-lc", "exec /home/agent/.cargo/bin/coyote"]
+
+network:
+  # Proxy-managed LLM providers: the proxy substitutes `proxy-managed` for
+  # the env var inside the sandbox and rewrites the auth header per
+  # serviceAuth at request time. Multiple domains may map to one service
+  # (e.g. jina) so they share a single credential.
+  serviceDomains:
+    api.openai.com: openai
+    api.anthropic.com: anthropic
+    generativelanguage.googleapis.com: gemini
+    api.cohere.ai: cohere
+    api.groq.com: groq
+    openrouter.ai: openrouter
+    api.ai21.com: ai21
+    api.cloudflare.com: cloudflare
+    api.deepinfra.com: deepinfra
+    api.deepseek.com: deepseek
+    api.mistral.ai: mistral
+    api.perplexity.ai: perplexity
+    api.voyageai.com: voyageai
+    api.x.ai: xai
+    api.jina.ai: jina
+    r.jina.ai: jina
+    qianfan.baidubce.com: ernie
+    api.hunyuan.cloud.tencent.com: hunyuan
+    api.minimax.chat: minimax
+    api.moonshot.cn: moonshot
+    dashscope.aliyuncs.com: qianwen
+    open.bigmodel.cn: zhipuai
+  serviceAuth:
+    openai:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    anthropic:
+      headerName: x-api-key
+      valueFormat: "%s"
+    gemini:
+      headerName: x-goog-api-key
+      valueFormat: "%s"
+    cohere:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    groq:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    openrouter:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    ai21:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    cloudflare:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    deepinfra:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    deepseek:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    mistral:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    perplexity:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    voyageai:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    xai:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    jina:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    ernie:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    hunyuan:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    minimax:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    moonshot:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    qianwen:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+    zhipuai:
+      headerName: Authorization
+      valueFormat: "Bearer %s"
+  allowedDomains:
+    # Coyote release + self-update + model-registry sync
+    - "github.com:443"
+    - "api.github.com:443"
+    - "raw.githubusercontent.com:443"
+    - "objects.githubusercontent.com:443"
+    - "*.githubusercontent.com:443"
+    # Coyote install paths (cargo install + uv + rustup + Python tool deps at runtime)
+    - "crates.io:443"
+    - "static.crates.io:443"
+    - "pypi.org:443"
+    - "files.pythonhosted.org:443"
+    - "astral.sh:443"
+    - "sh.rustup.rs:443"
+    - "static.rust-lang.org:443"
+
+    # LLM model OAuth + API endpoints
+    - "claude.ai:443"
+    - "console.anthropic.com:443"
+    - "accounts.google.com:443"
+    # *.googleapis.com covers oauth2 + userinfo + VertexAI regional endpoints
+    # (*-aiplatform.googleapis.com). Do not narrow without re-checking VertexAI.
+    - "*.googleapis.com:443"
+
+    # Bedrock and GitHub Models use signed / GitHub-PAT auth that the proxy
+    # cannot rewrite. Domains are allow-listed; credentials must be injected
+    # separately (see README "Extending").
+    - "*.amazonaws.com:443"
+    - "models.inference.ai.azure.com:443"
+
+credentials:
+  sources:
+    openai:
+      env:
+        - OPENAI_API_KEY
+    anthropic:
+      env:
+        - ANTHROPIC_API_KEY
+    gemini:
+      env:
+        - GEMINI_API_KEY
+        - GOOGLE_API_KEY
+    cohere:
+      env:
+        - COHERE_API_KEY
+    groq:
+      env:
+        - GROQ_API_KEY
+    openrouter:
+      env:
+        - OPENROUTER_API_KEY
+    ai21:
+      env:
+        - AI21_API_KEY
+    cloudflare:
+      env:
+        - CLOUDFLARE_API_KEY
+    deepinfra:
+      env:
+        - DEEPINFRA_API_KEY
+    deepseek:
+      env:
+        - DEEPSEEK_API_KEY
+    mistral:
+      env:
+        - MISTRAL_API_KEY
+    perplexity:
+      env:
+        - PERPLEXITY_API_KEY
+    voyageai:
+      env:
+        - VOYAGE_API_KEY
+    xai:
+      env:
+        - XAI_API_KEY
+    jina:
+      env:
+        - JINA_API_KEY
+    ernie:
+      env:
+        - ERNIE_API_KEY
+    hunyuan:
+      env:
+        - HUNYUAN_API_KEY
+    minimax:
+      env:
+        - MINIMAX_API_KEY
+    moonshot:
+      env:
+        - MOONSHOT_API_KEY
+    qianwen:
+      env:
+        - DASHSCOPE_API_KEY
+    zhipuai:
+      env:
+        - ZHIPUAI_API_KEY
+
+environment:
+  variables:
+    IS_SANDBOX: "1"
+    COYOTE_LOG_LEVEL: INFO
+    COYOTE_CONFIG_DIR: /home/agent/.config/coyote
+  proxyManaged:
+    - OPENAI_API_KEY
+    - ANTHROPIC_API_KEY
+    - GEMINI_API_KEY
+    - GOOGLE_API_KEY
+    - COHERE_API_KEY
+    - GROQ_API_KEY
+    - OPENROUTER_API_KEY
+    - AI21_API_KEY
+    - CLOUDFLARE_API_KEY
+    - DEEPINFRA_API_KEY
+    - DEEPSEEK_API_KEY
+    - MISTRAL_API_KEY
+    - PERPLEXITY_API_KEY
+    - VOYAGE_API_KEY
+    - XAI_API_KEY
+    - JINA_API_KEY
+    - ERNIE_API_KEY
+    - HUNYUAN_API_KEY
+    - MINIMAX_API_KEY
+    - MOONSHOT_API_KEY
+    - DASHSCOPE_API_KEY
+    - ZHIPUAI_API_KEY
+
+commands:
+  install:
+    - command: |
+        sudo apt-get update &&
+        sudo apt-get install -y \
+          jq curl git \
+          build-essential pkg-config \
+          cmake \
+          clang libclang-dev \
+          musl-tools \
+          libssl-dev \
+          pandoc \
+          bzip2
+      user: "1000"
+      description: Install system prerequisites (including pandoc for fetch_url_via_curl)
+    - command: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        if [ -f "$HOME/.local/bin/uv" ]; then
+          printf '#!/bin/sh\nexec uv tool run "$@"\n' > "$HOME/.local/bin/uvx"
+          chmod +x "$HOME/.local/bin/uvx"
+        fi
+      user: "1000"
+      description: Install uv and write a uvx shell wrapper (the installer may place a macOS binary at this path on Docker-for-Mac hosts, which the Linux container cannot execute)
+    - command: |
+        set -euo pipefail
+        USQL_VERSION=0.21.4
+        ARCH=$(uname -m)
+        case "$ARCH" in
+          x86_64) USQL_ARCH=amd64 ;;
+          aarch64) USQL_ARCH=arm64 ;;
+          *) echo "Unsupported arch for usql install: $ARCH" >&2; exit 1 ;;
+        esac
+        TMPDIR=$(mktemp -d)
+        trap 'rm -rf "$TMPDIR"' EXIT
+        curl -fsSL --retry 3 "https://github.com/xo/usql/releases/download/v${USQL_VERSION}/usql_static-${USQL_VERSION}-linux-${USQL_ARCH}.tar.bz2" -o "$TMPDIR/usql.tar.bz2"
+        tar -xjf "$TMPDIR/usql.tar.bz2" -C "$TMPDIR"
+        sudo install -m 0755 "$TMPDIR/usql_static" /usr/local/bin/usql
+      user: "1000"
+      description: Install the usql universal SQL CLI (used by the built-in sql agent and execute_sql_code tool)
+    - command: |
+        curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | \
+          sh -s -- -y \
+          --default-toolchain stable \
+          --profile minimal \
+          --target x86_64-unknown-linux-musl
+        . "$HOME/.cargo/env"
+        cargo install --locked coyote-ai
+      user: "1000"
+      description: Install Coyote AI CLI via Rust's Cargo
+    - command: |
+        . "$HOME/.cargo/env"
+        cargo install --locked iwec
+      user: "1000"
+      description: Install the IWE MCP server binary (iwec) used by the built-in iwe MCP server and iwe-knowledge-base skill
+    - command: |
+        . "$HOME/.cargo/env"
+        cargo install --locked ast-grep
+      user: "1000"
+      description: Install ast-grep, used by the built-in ast_grep structural code search tool (and the explore agent)
+
+  startup:
+    - command:
+        [
+          "sh",
+          "-c",
+          'test -f "$HOME/.config/coyote/config.yaml" || coyote --info >/dev/null 2>&1 || true',
+        ]
+      user: "1000"
+      background: false
+      description: Bootstrap Coyote config directory on first sandbox start
+
+agentContext: |
+  ## Sandbox environment
+
+  You are running inside a Docker sandbox launched via `sbx run coyote`. The
+  user's project workspace is mounted at its absolute host path and is the
+  current working directory. `sudo` is passwordless; use it for system
+  package installs.
+
+  Coyote's configuration lives at `~/.config/coyote/` and logs at
+  `~/.cache/coyote/coyote.log`. Persistence is enabled, so config, sessions,
+  vault state, OAuth tokens, and installed tools survive sandbox restarts.
+
+  LLM provider credentials are forwarded by the sandbox HTTP proxy. The
+  following provider env vars are recognized - export the ones you use on
+  the host before running `sbx run coyote`:
+
+    OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY / GOOGLE_API_KEY,
+    COHERE_API_KEY, GROQ_API_KEY, OPENROUTER_API_KEY, AI21_API_KEY,
+    CLOUDFLARE_API_KEY, DEEPINFRA_API_KEY, DEEPSEEK_API_KEY,
+    MISTRAL_API_KEY, PERPLEXITY_API_KEY, VOYAGE_API_KEY, XAI_API_KEY,
+    JINA_API_KEY, ERNIE_API_KEY, HUNYUAN_API_KEY, MINIMAX_API_KEY, 
+    MOONSHOT_API_KEY, DASHSCOPE_API_KEY (Qwen), ZHIPUAI_API_KEY
+
+  Inside the sandbox these appear as the placeholder string `proxy-managed`;
+  the proxy substitutes the real value at request time. OAuth flows for
+  Claude Pro/Max and Gemini are also allow-listed.
+
+  Bedrock (AWS) and VertexAI (Google Cloud) use signed/OAuth-token requests
+  that the proxy cannot rewrite. Their domains are allow-listed but you must
+  inject credentials yourself via `sbx run --env AWS_ACCESS_KEY_ID=...` or
+  a mixin kit that mounts a service-account JSON.
+
+  Useful first-run commands:
+  - `coyote --info`          # show config paths and resolved settings
+  - `coyote --list-secrets`  # initialise the local vault
+  - `coyote --authenticate <client>`  # OAuth flow (Claude Pro/Max, Gemini)

assets/sbx-vault-mixins/aws_secrets_manager/spec.yaml

@@ -0,0 +1,33 @@
+schemaVersion: "1"
+kind: mixin
+name: vault-aws-secrets-manager
+description: >
+  Installs the AWS CLI v2 so the Coyote vault can read secrets from AWS
+  Secrets Manager inside the sandbox. The AWS Rust SDK does not strictly
+  require the CLI, but most users authenticate via `aws sso login` or
+  `aws configure`, which need the CLI to be installed. After install, run
+  the appropriate auth command in the sandbox; cached credentials persist
+  for the lifetime of the sandbox.
+
+network:
+  allowedDomains:
+    - "awscli.amazonaws.com:443"
+    - "sts.amazonaws.com:443"
+    - "*.sts.amazonaws.com:443"
+    - "*.secretsmanager.amazonaws.com:443"
+    - "*.amazonaws.com:443"
+    - "*.awsapps.com:443"
+
+commands:
+  install:
+    - command: |
+        set -euo pipefail
+        sudo apt-get update
+        sudo apt-get install -y unzip
+        ARCH=$(uname -m)
+        curl -sSL "https://awscli.amazonaws.com/awscli-exe-linux-${ARCH}.zip" -o /tmp/awscliv2.zip
+        unzip -q /tmp/awscliv2.zip -d /tmp
+        sudo /tmp/aws/install
+        rm -rf /tmp/awscliv2.zip /tmp/aws
+      user: "1000"
+      description: Install AWS CLI v2 from the official installer

assets/sbx-vault-mixins/azure_key_vault/spec.yaml

@@ -0,0 +1,24 @@
+schemaVersion: "1"
+kind: mixin
+name: vault-azure-key-vault
+description: >
+  Installs the Azure CLI (`az`) so the Coyote vault can read secrets from
+  Azure Key Vault inside the sandbox. After install, run `az login` in the
+  sandbox to authenticate; the session token persists for the lifetime of
+  the sandbox.
+
+network:
+  allowedDomains:
+    - "aka.ms:443"
+    - "packages.microsoft.com:443"
+    - "azurecliprod.blob.core.windows.net:443"
+    - "login.microsoftonline.com:443"
+    - "graph.microsoft.com:443"
+    - "management.azure.com:443"
+    - "*.vault.azure.net:443"
+
+commands:
+  install:
+    - command: "curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash"
+      user: "1000"
+      description: Install Azure CLI via Microsoft's official install script

assets/sbx-vault-mixins/gcp_secret_manager/spec.yaml

@@ -0,0 +1,34 @@
+schemaVersion: "1"
+kind: mixin
+name: vault-gcp-secret-manager
+description: >
+  Installs the Google Cloud CLI (`gcloud`) so the Coyote vault can read
+  secrets from GCP Secret Manager inside the sandbox. The GCP Rust SDK does
+  not strictly require the CLI, but most users authenticate via
+  `gcloud auth application-default login`, which needs the CLI to be
+  installed. After install, run that command in the sandbox; the ADC file
+  persists for the lifetime of the sandbox.
+
+network:
+  allowedDomains:
+    - "packages.cloud.google.com:443"
+    - "accounts.google.com:443"
+    - "oauth2.googleapis.com:443"
+    - "secretmanager.googleapis.com:443"
+    - "cloudresourcemanager.googleapis.com:443"
+    - "*.googleapis.com:443"
+
+commands:
+  install:
+    - command: |
+        set -euo pipefail
+        sudo apt-get update
+        sudo apt-get install -y apt-transport-https ca-certificates gnupg
+        echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" \
+          | sudo tee /etc/apt/sources.list.d/google-cloud-sdk.list >/dev/null
+        curl -sSL https://packages.cloud.google.com/apt/doc/apt-key.gpg \
+          | sudo gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg
+        sudo apt-get update
+        sudo apt-get install -y google-cloud-cli
+      user: "1000"
+      description: Install gcloud CLI from Google's official apt repository

assets/sbx-vault-mixins/gopass/spec.yaml

@@ -0,0 +1,30 @@
+schemaVersion: "1"
+kind: mixin
+name: vault-gopass
+description: >
+  Installs `gopass` and `gpg` so the Coyote vault can read secrets from a
+  gopass store inside the sandbox. The store must be cloned manually
+  (gopass walks a user-specific git remote, so v1 only allowlists github.com
+  and gitlab.com; add other hosts via a user mixin if needed). After install,
+  run `gopass setup` or `gopass clone <remote>` in the sandbox.
+
+network:
+  allowedDomains:
+    - "github.com:443"
+    - "api.github.com:443"
+    - "objects.githubusercontent.com:443"
+    - "gitlab.com:443"
+
+commands:
+  install:
+    - command: |
+        set -euo pipefail
+        sudo apt-get update
+        sudo apt-get install -y gnupg2 git
+        GOPASS_VERSION="1.15.13"
+        ARCH=$(dpkg --print-architecture)
+        curl -sSL "https://github.com/gopasspw/gopass/releases/download/v${GOPASS_VERSION}/gopass_${GOPASS_VERSION}_linux_${ARCH}.deb" -o /tmp/gopass.deb
+        sudo dpkg -i /tmp/gopass.deb
+        rm -f /tmp/gopass.deb
+      user: "1000"
+      description: Install gnupg2, git, and gopass from the official .deb release

assets/sbx-vault-mixins/one_password/spec.yaml

@@ -0,0 +1,31 @@
+schemaVersion: "1"
+kind: mixin
+name: vault-one-password
+description: >
+  Installs the 1Password CLI (`op`) so the Coyote vault can decrypt secrets
+  inside the sandbox. After install, run `op signin` in the sandbox to
+  authenticate; credentials persist for the lifetime of the sandbox.
+
+network:
+  allowedDomains:
+    - "downloads.1password.com:443"
+    - "cache.agilebits.com:443"
+    - "my.1password.com:443"
+    - "my.1password.eu:443"
+    - "my.1password.ca:443"
+    - "events.1password.com:443"
+
+commands:
+  install:
+    - command: |
+        set -euo pipefail
+        sudo apt-get update
+        sudo apt-get install -y unzip
+        OP_VERSION="v2.30.3"
+        ARCH=$(dpkg --print-architecture)
+        curl -sSL "https://cache.agilebits.com/dist/1P/op2/pkg/${OP_VERSION}/op_linux_${ARCH}_${OP_VERSION}.zip" -o /tmp/op.zip
+        sudo unzip -od /usr/local/bin /tmp/op.zip op
+        sudo chmod +x /usr/local/bin/op
+        rm -f /tmp/op.zip
+      user: "1000"
+      description: Install 1Password CLI from the official archive

assets/skills/ai-slop-remover/SKILL.md

@@ -0,0 +1,39 @@
+---
+description: Detect and remove AI slop from code and prose; produce output indistinguishable from a senior engineer's.
+---
+You are reviewing or generating content. Apply these standards strictly. The goal is output that reads like it was written by a competent human professional, not an AI.
+
+## Code
+
+**No useless comments.** A comment is useless if it restates the code:
+- BAD: `// Increment counter` above `counter += 1`
+- BAD: `/// Returns the user's name.` on `fn user_name() -> &str`
+- GOOD: Comments that explain a non-obvious WHY: a constraint, an invariant, a workaround for a specific bug, behavior that would surprise a reader.
+
+If removing a comment wouldn't confuse a future reader, the comment shouldn't exist.
+
+**No emojis** unless the user explicitly asked for them.
+
+**No defensive handling for impossible cases.** If a function only receives valid input from internal callers, don't pretend otherwise. Validate at system boundaries (user input, external APIs, file I/O); trust internal code.
+
+**No over-engineering for hypothetical futures.** Three similar lines of code is fine. Premature abstractions are worse than duplication.
+
+**No backwards-compatibility cruft for unreleased code.** If a function isn't called yet, just change it. Don't add `_unused` prefixes, "// removed" comments, or wrapper layers "for migration."
+
+**Names should be honest.** A function called `get_user` should not mutate state. A field called `count` should not be a function. A method that can fail should return `Result`, not panic.
+
+## Prose
+
+**No flattery.** Don't start with "Great question!" or "That's a really good idea!" Just respond.
+
+**No filler.** "It's important to note that" — delete. "Let me explain" — just explain. "I'll go ahead and" — just do it.
+
+**No status updates.** "I'm going to help you with that" — just help.
+
+**Match the user's terseness.** Brief user, brief reply. Detailed user, detailed reply.
+
+**No multi-paragraph docstrings.** One short line max. If the function needs paragraphs to explain, the function is doing too much.
+
+## When in doubt
+
+Ask: "Would a senior engineer write this in a code review or a Slack message?" If not, cut it.

assets/skills/code-review/SKILL.md

@@ -0,0 +1,124 @@
+---
+description: Conduct a thorough code review focused on correctness, clarity, tests, and footguns. Grants read-only filesystem access for inspecting code.
+enabled_tools: fs_read, fs_grep, fs_glob, fs_cat, fs_ls
+---
+You are reviewing code. Use the filesystem tools (`fs_read`, `fs_grep`, `fs_glob`, `fs_cat`, `fs_ls`) to inspect files. Apply this checklist in order; stop at the first category where you find substantial issues, since fixing those usually shifts the rest of the review.
+
+## Investigation workflow
+
+Before reviewing, build a mental model of the surrounding code:
+
+- `fs_ls` the directories that contain the changed files.
+- `fs_grep` for the symbols being added/modified to see existing callers and tests.
+- `fs_read` neighboring files in the same module to understand local conventions.
+- `fs_glob` for test files that might cover this area.
+
+A review without context is just a syntax check.
+
+## Reviewing a diff
+
+When you only see a hunk (not the whole file), the default context is sparse — usually 3 lines on either side. You see what changed but rarely the function signature, the caller, or the test. Read deliberately to recover what the diff omits.
+
+### Read around the hunk
+
+The `@@ -120,8 +120,12 @@` header gives you the line numbers in the old (`-`) and new (`+`) file. Read 20–40 lines around the hunk to see the enclosing function:
+
+```
+fs_read --path "src/auth.rs" --offset 110 --limit 40
+```
+
+You're recovering: the function signature, the return type, what unchanged portions do, and whether the hunk's logic fits its enclosing scope.
+
+### Read the callers of anything changed
+
+If a hunk changes a function's body or its signature, grep for the name to find callers and check whether the change ripples:
+
+```
+fs_grep --pattern "changed_function" --include "*.rs"
+```
+
+Skip the test files in this search; do the test sweep next.
+
+### Read the tests for the change
+
+Even if the diff doesn't touch test files, check whether tests exist for what's changing:
+
+```
+fs_grep --pattern "changed_function" --include "*_test.rs"
+fs_grep --pattern "changed_function" --include "tests/*"
+```
+
+Absence of tests for a changed function is itself a finding ("changes function X but no test references it; regressions won't be caught").
+
+### Diff-shaped issues to watch for
+
+These are review findings that only surface in a diff context, not in a whole-file read:
+
+- **Renames** (`diff --git a/old.rs b/new.rs`) — `fs_grep` for the old path to find imports that need updating but weren't.
+- **Signature changes** — verify all callers compile against the new signature. Compiler-checked languages catch some of this; dynamic languages don't.
+- **New code path without new tests** — usually a missing test. Flag it.
+- **Removed code with tests still present** — the tests probably need updating too.
+- **The "dog that didn't bark"** — what's obvious by its ABSENCE? A new field with no migration, a new error path with no test, a public API change with no changelog, a new config option with no documentation. Flag these as missing pieces, not as things to add later.
+
+### Scope discipline
+
+A diff review is a review of THE CHANGE, not the whole file:
+
+- Don't moralize about pre-existing code unless the diff makes it worse.
+- Don't suggest refactors outside the scope of the change. ("This whole module could be cleaner" is not actionable feedback on a 5-line patch.)
+- If you spot unrelated bugs while reading context, mention them briefly but separately: prefix with `Pre-existing, out of scope:` so the author knows which findings block their merge and which are FYI.
+- The author's job is to ship THIS change. Your job is to catch what's wrong with THIS change.
+
+## 1. Correctness
+
+- Does the change actually do what it claims? Does it solve the stated problem?
+- Edge cases: empty inputs, max sizes, concurrent access, error paths, partial failures.
+- Off-by-one errors, type confusion, null/None handling, integer overflow.
+- Race conditions and ordering assumptions across threads, async tasks, or distributed components.
+- Resource cleanup: file handles, locks, network connections, transactions.
+
+## 2. Tests
+
+- Do the tests test BEHAVIOR, not implementation? (Tests of `private_helper()` are usually a smell.)
+- Will they fail when the code regresses? Or are they tautological (e.g., `assert!(x.is_empty() || !x.is_empty())`)?
+- Do they cover the unhappy paths, not just the happy ones?
+- Is there a missing test for the specific bug or feature being added? `fs_grep` for the function name in test files to check.
+
+## 3. Clarity
+
+- Are names accurate? `get_user` that mutates is a lie; rename or split.
+- Could a competent reader understand this without comments?
+- Is there a simpler way to express the same logic?
+- Is the function doing one thing, or several things glued together?
+
+## 4. Coupling
+
+- Does this change increase coupling between modules unnecessarily?
+- Is the new code reaching into internals it shouldn't (private fields exposed, deep import paths)?
+- Could the change be expressed as a smaller diff that doesn't ripple through unrelated files?
+
+## 5. Footguns
+
+- Could a future maintainer easily misuse this API?
+- Are invariants enforced by types, or just by convention?
+- Are error types specific enough to be actionable?
+- Is there a documented or implicit ordering requirement that's easy to break?
+
+## What to flag
+
+- Correctness bugs.
+- Missing error handling at trust boundaries.
+- Race conditions.
+- Tests that won't catch regressions.
+- Security issues (injection, auth, exposed secrets).
+
+## What to let go
+
+- Style differences that aren't in the codebase's existing conventions.
+- "I would have done it differently" preferences.
+- Comments and naming choices that match existing patterns in the same file.
+- Micro-optimizations in code that isn't on a hot path.
+
+## Tone
+
+Direct, specific, focused on the code. No flattery, no padding. If something is wrong, say so plainly with the file path and line reference and the reason. If something is good and non-obvious, briefly call it out so the author knows it's intentional.

assets/skills/delegation-protocol/SKILL.md

@@ -0,0 +1,69 @@
+---
+description: Structured 6-section delegation template and session-continuity rules for orchestrating sub-agents. Load before spawning any agent.
+---
+You are delegating work to a sub-agent. The sub-agent has not seen the codebase or the conversation — your prompt IS its entire context. Treat delegation as writing a contract: explicit, scoped, and verifiable.
+
+## The 6-section template (every delegation)
+
+Every `agent__spawn` prompt MUST include all six sections. Vague prompts produce vague results and waste tokens on re-exploration the orchestrator already did.
+
+```
+## TASK
+[One atomic goal. One verb. One outcome. No "and also".]
+
+## EXPECTED OUTCOME
+[Concrete deliverables and success criteria. "I will know this is done when ..."]
+
+## REQUIRED TOOLS
+[Explicit allowlist: fs_read, fs_grep, etc. Prevents tool sprawl.]
+
+## MUST DO
+[Exhaustive requirements. Leave nothing implicit. If you'd be annoyed by the agent not doing X, list X.]
+
+## MUST NOT DO
+[Forbidden actions. Anticipate rogue behavior. "Do not modify files outside src/auth/."]
+
+## CONTEXT
+[File paths, code snippets, existing patterns, constraints. Paste actual code lines from prior exploration — not just file paths.]
+```
+
+## Session continuity (NON-NEGOTIABLE)
+
+Every `agent__spawn` result includes a session_id. **Use it.**
+
+- Task failed/incomplete → resume with `session_id` + a tight "Fix: <error>" prompt.
+- Follow-up on a result → resume with `session_id` + "Also: <question>".
+- Multi-turn with the same agent → always resume. Never start fresh.
+
+Starting a fresh agent for a follow-up forces it to re-read every file it already read. That's 70%+ wasted tokens, plus the agent loses the reasoning it built up.
+
+After every delegation, **store the session_id compression-safe** for potential continuation. Long sessions compress: chat history gets replaced by a summary, and a session_id that exists only in chat history is unresumable afterward. Embed it in the todo item for that work — `todo__add "Implement auth endpoint (coder ses_abc123)"` — or in your run-state memory file. The todo list and memory survive compression; the conversation does not.
+
+## Skill nudges to delegates
+
+Sub-agents have their own skills. Nudge them in the CONTEXT section:
+
+> "Load `code-review` before evaluating the diff."
+> "Load `frontend-ui-ux` before editing component files."
+> "Load `git-master` before touching history."
+
+A one-line nudge saves the delegate a `skill__list` turn.
+
+## Verification after delegation
+
+A delegation is NOT complete when the sub-agent returns. It is complete when YOU have verified:
+
+1. Did it work as expected? (Did the file change? Did the test pass?)
+2. Did it follow existing codebase patterns?
+3. Did the EXPECTED OUTCOME actually materialize?
+4. Did it respect MUST DO and MUST NOT DO?
+
+If any answer is no → resume the session with a corrective prompt. Do not re-spawn from scratch.
+
+## Anti-patterns
+
+- "Follow existing patterns" with no snippet → agent guesses, often wrong
+- Multi-goal prompts → agent does the easy one, skips the rest
+- Missing MUST NOT DO → agent over-reaches into unrelated files
+- Discarding session_id on failure → forced re-exploration, wasted tokens
+- Re-spawning instead of resuming for a 1-line fix → 10x cost

assets/skills/diagnostics/SKILL.md

@@ -0,0 +1,40 @@
+---
+description: Systematic troubleshooting of technical issues (services, networking, containers, OS) by running diagnostic commands directly instead of asking the user to.
+enabled_tools: execute_command
+---
+A technical problem needs diagnosing. Apply this methodology strictly. Use the `execute_command` tool to gather
+evidence yourself — never ask the user to run commands and paste output back.
+
+## Loop
+
+1. **Reproduce first.** Run the failing thing and read the actual error before theorizing.
+2. **Ask "what changed?"** Updates, config edits, reboots, expirations. Check recent history early.
+3. **Cheap checks first.** Service running/enabled? Interface up? Disk full? DNS resolving? Clock right?
+4. **Isolate by layer, one variable at a time.** Network: link → IP → routing → DNS → transport → app.
+   Software: process → logs → config → deps/permissions → environment. Containers: daemon → image → container →
+   logs → mounts/networks → host.
+5. **State each hypothesis in one line before testing it.** Pivot openly when disproved.
+6. **Fix root cause, then verify** by re-running the original failing operation. No verification, no fix.
+
+## Command Discipline
+
+- Non-interactive and bounded, always: `--no-pager`, `-n`/`--since` on logs, `timeout 10` on anything that might
+  hang, `-c` on ping. No TUIs — use batch modes.
+- Unprivileged first; `sudo` only when required, stating why.
+- Web-search exact quoted error strings (with software name + version) for unfamiliar errors.
+
+## Safety Tiers
+
+1. **Read-only** (status, logs, ls, cat, ping, dig): run freely.
+2. **Reversible changes** (service restart, interface bounce, config edit): announce in one sentence, back up files
+   first (`cp file file.bak.$(date +%s)`), then do it.
+3. **Destructive** (data/volume deletion, formatting, `dd`, package removal, firewall flush): require explicit user
+   confirmation with the exact command and a rollback plan. Never on your own judgment.
+
+Redact any secrets appearing in command output. Never disable security controls as a "fix". Stop and present options
+if evidence suggests failing hardware or data-loss risk.
+
+## Reporting
+
+Lead with findings, show trimmed key evidence, and close resolved issues with: root cause → fix → verification →
+prevention.

assets/skills/frontend-ui-ux/SKILL.md

@@ -0,0 +1,67 @@
+---
+description: Designer-turned-developer who crafts stunning UI/UX even without design mockups. Grants filesystem read/write access for editing component files.
+enabled_tools: fs_read, fs_write, fs_patch, fs_grep, fs_glob, fs_cat, fs_ls, fs_mkdir
+---
+You are doing frontend work. Use the filesystem tools to read, write, and patch component files. Treat UI/UX as a discipline, not a polish step at the end.
+
+## Investigate before editing
+
+Before changing a component:
+
+- `fs_ls` the component's directory to see siblings and tests.
+- `fs_read` the component itself.
+- `fs_grep` for the component's usages across the codebase — your edits affect every caller.
+- `fs_grep` for the project's design tokens, theme variables, or styling primitives (e.g., `--color-`, `theme.spacing`, `tw-`).
+- Read existing similar components to match conventions.
+
+## Visual hierarchy
+
+Every screen has a focal point. Identify it before laying out anything else:
+
+- One primary action per view. Make it visually dominant.
+- Secondary actions are present but visibly subordinate.
+- Tertiary actions can be tucked into menus or hidden behind affordances.
+
+## Spacing and rhythm
+
+- Use the project's existing spacing scale (4px, 8px, custom — match what's already there). Don't introduce one-off values.
+- Larger spacing = stronger grouping break. Inside a card, tight; between cards, looser.
+- White space is not wasted space. It's the difference between "professional" and "cramped."
+
+## Typography
+
+- Two or three sizes per view, max. More than that is noise.
+- Line-height: 1.4-1.6 for body, tighter for headlines.
+- Don't center long paragraphs. Left-align (or right-align for RTL).
+
+## Color
+
+- Use the project's existing palette. If you need a color that isn't there, you're probably overdesigning.
+- Contrast matters: aim for WCAG AA at minimum (4.5:1 for body text, 3:1 for large text).
+- Don't use color as the sole signal — pair with icons, labels, or shape changes for accessibility.
+
+## Component conventions
+
+When adding a new component:
+
+- Match the existing structure: where do props go, where do styles go, where do tests go?
+- `fs_read` two or three similar components first to internalize the patterns.
+- If the codebase uses CSS modules / styled-components / Tailwind / Vanilla Extract — use the same. Don't introduce a new system.
+- Co-locate tests and stories with the component, matching the existing convention.
+
+## Forms
+
+- Label every input. Placeholder text is not a label.
+- Show validation errors near the field, not in a banner at the top.
+- Validate on blur, not on every keystroke. Show success states only after the user has interacted.
+- Required fields: mark visually AND in the input's accessibility attributes.
+
+## Loading and empty states
+
+- Empty states are an opportunity, not a fallback. Tell the user what they can do, not "no data."
+- Loading: show structure (skeletons) when you know what's coming. Spinners are for indeterminate waits.
+- Errors: explain WHAT failed and what the user can do about it. "Something went wrong" is useless.
+
+## When unsure
+
+Ship the boring version. A well-executed boring design beats an under-executed clever one every time.

assets/skills/git-master/SKILL.md

@@ -0,0 +1,58 @@
+---
+description: Methodology for atomic commits, rebase surgery, and clean git history. Grants shell access for running git commands.
+enabled_tools: execute_command
+---
+You are operating on a git repository. Apply these conventions strictly. Use the `execute_command` tool to run git commands.
+
+## Atomic commits
+
+Each commit represents one logical change. If the commit message needs the word "and," the change is too large; split it. Mixed concerns in one commit are nearly impossible to revert cleanly later.
+
+## Commit messages
+
+- Subject line: imperative mood, ≤50 characters, no trailing period.
+- Blank line.
+- Body: explain WHY, not WHAT. The diff shows what changed.
+- Reference issues by URL or canonical ID, not by free-form description.
+
+## Rebase, don't merge
+
+- `git rebase -i origin/main` before opening a PR.
+- Squash WIP commits and fixups; keep only meaningful commits in the final history.
+- Never rebase a branch others may have based work on. If unsure, ask.
+
+## Conflict resolution
+
+- Read both sides carefully before resolving. Don't reflexively take "ours" or "theirs."
+- After resolving, run tests before continuing the rebase.
+- For non-trivial conflicts, document the resolution choice in the resulting commit body.
+
+## Investigation workflow
+
+Use `execute_command` to run these inspection commands when chasing down history:
+
+- `git log -p <file>` — see how a file evolved over time.
+- `git log -S '<string>'` (pickaxe) — find when a string was added or removed.
+- `git log --all --grep '<pattern>'` — search commit messages.
+- `git blame -L <start>,<end> <file>` — current authorship for a line range.
+- `git diff <ref1>..<ref2> -- <path>` — narrow diffs to specific paths.
+- `git bisect start && git bisect bad && git bisect good <ref>` — narrow down regressions.
+
+## Safety checklist before destructive operations
+
+Before running anything that rewrites history or deletes refs:
+
+- `git status` — confirm clean working tree.
+- `git branch --show-current` — confirm which branch you're on.
+- `git log -3 --oneline` — confirm what's about to be moved.
+
+## What to never do
+
+- Force-push to shared branches (`main`, release branches, anything teammates pull from).
+- `git reset --hard` without confirming current branch and verifying the reflog can recover.
+- `git push --no-verify` to skip hooks — fix the underlying issue instead.
+- Commit secrets, even temporarily. Once pushed, treat as compromised; rotate.
+
+## When unsure, read state first
+
+Before guessing at a fix, run `git status`, `git log -5 --oneline`, and `git diff` (or `git diff --staged`) to see the actual state. Don't operate on assumptions.

assets/skills/handoff-protocol/SKILL.md

@@ -0,0 +1,78 @@
+---
+description: Schema and discipline for writing and reading step handoff documents - the only channel between implementation steps. Evidence must be pasted, downstream plan changes proposed not imposed. Grants filesystem access for reading and writing handoffs.
+enabled_tools: fs_read, fs_cat, fs_ls, fs_write
+---
+A handoff is the ONLY channel between step N and step N+1. The next executor runs in a fresh session: it sees the plan repo, the code, and this document — nothing else. Whatever you learned that isn't in the handoff (or in `plans/NOTES.md`) is lost. Write accordingly.
+
+Handoffs live in `plans/handoffs/`, named to match their step plan: `plans/handoffs/03-<slug>.md` for `plans/steps/03-<slug>.md`.
+
+## Required schema (writer)
+
+Frontmatter:
+
+```yaml
+---
+step: 3
+title: Add retry policy to the fetch client
+result: complete   # complete | partial | blocked
+---
+```
+
+Sections, all mandatory (write "None" rather than omitting — an absent section is indistinguishable from a forgotten one):
+
+| Section | Contents |
+|---|---|
+| Summary | 2-4 sentences: what exists now that didn't before |
+| Completed | Task-by-task, mirroring the plan's Tasks section |
+| Not completed | Deferred or dropped tasks, each WITH a reason |
+| Deviations | Every departure from the plan: what the plan said, what you did, why |
+| Downstream plan updates | Edge-case annotations made directly (which plan, which section) and proposed diffs awaiting approval (see below) |
+| Edge cases discovered | Found during implementation — including ones you handled, so the next step knows they're covered |
+| Evidence | Pasted verbatim: format/lint/build/test commands, exit codes, salient output lines. Note pre-existing failures explicitly |
+| Notes for next step | Warnings, gotchas, invariants the next executor must not violate |
+
+## Evidence rules
+
+Assertions are not evidence. "Tests pass" is a claim; this is evidence:
+
+```
+$ cargo test
+   ...
+test result: ok. 47 passed; 0 failed; exit code 0
+```
+
+- Paste the command, the exit code, and the decisive output lines (not the full log).
+- Evidence must reflect the FINAL state of the code — collected after formatting and linting, re-collected after any post-review fix.
+- If a check was skipped (no formatter configured, etc.), say so explicitly.
+
+## Downstream plan updates: annotate vs propose
+
+Two classes, with different authority:
+
+- **Annotations (make directly).** Adding an entry to a later plan's Edge cases section. Additive, non-scope-changing. Record each in Downstream plan updates.
+- **Proposals (never apply directly).** Anything touching a later plan's Objective, Tasks, Acceptance criteria, or Out of scope. Write the change as a fenced before/after diff in Downstream plan updates and flag it at the approval gate. The user applies or rejects it.
+
+The executor who rationalizes a shortcut must not be able to quietly rewrite the spec they'll be judged against — that is why scope changes route through the user.
+
+## Rolling notes vs handoff
+
+- **Handoff**: step-scoped. What happened in THIS step.
+- **`plans/NOTES.md`**: durable, step-independent facts ("config loader lowercases all keys", "integration tests need docker running"). Append; never rewrite others' entries. Without this file, facts discovered in step 2 are invisible to step 7, because step 7 reads only step 6's handoff.
+
+## Reading a handoff (start of a step)
+
+1. Check `result`. `partial` or `blocked` → read Not completed first; your plan's `depends_on` may not actually be satisfied. Escalate rather than build on missing ground.
+2. Trust what has pasted evidence. Re-verify bare assertions before depending on them.
+3. Apply Notes for next step and any approved proposals aimed at your step, BEFORE the staleness check.
+4. Treat Deviations as corrections to your mental model of the codebase — the plans upstream of you described code that no longer exists as written.
+5. Read `plans/NOTES.md` — handoffs chain pairwise; the rolling notes are the only cumulative memory.
+
+## Anti-patterns
+
+- "All tests pass" with nothing pasted — a claim, not a handoff
+- Omitting a section instead of writing "None" — forgotten or empty, the reader can't tell
+- Editing a later plan's Tasks or scope directly instead of proposing a diff
+- Burying a major deviation in prose instead of the Deviations section
+- Durable facts in the handoff only — lost after one more step
+- Evidence collected before the formatter ran — the pasted output describes bytes that no longer exist
+- Writing the handoff before the completion gate (todos done or deferred-with-reason) is satisfied

assets/skills/iwe-knowledge-base/SKILL.md

@@ -0,0 +1,65 @@
+---
+description: Navigate and curate markdown knowledge bases (plan repos, spec repos, companion docs) with IWE graph tools. Load when the workspace is or contains a markdown knowledge base and the task involves finding, reading, or reorganizing plans, specs, designs, or notes. Activates the iwe MCP server rooted at the current directory.
+enabled_mcp_servers: iwe
+---
+You are working with a markdown knowledge base through IWE, a graph-based knowledge tool. The `iwe` MCP server is rooted at the current working directory (`--project .`), so the knowledge base is the directory Coyote was launched in. IWE derives structure from links: a link on its own line is an *inclusion link* (parent-child hierarchy); a link inside text is an *inline reference* (cross-reference, produces backlinks). The server watches the filesystem, so external edits are picked up automatically — never ask for a restart.
+
+## When to use this (and when not)
+
+Use IWE tools when the task involves a corpus of markdown documents: plan repositories, spec/design collections, companion docs repos, meeting notes, PKM vaults.
+
+Do NOT use IWE tools for:
+
+- **Agent memory** (`.coyote/memory/`, `COYOTE.md`) — use the `memory__*` tools; they own the index conventions there.
+- **Semantic/similarity search over documents** — that is RAG's job. IWE search is fuzzy title/key matching plus structural traversal, not embeddings.
+- **Source code** — IWE only understands markdown.
+
+If unsure whether the current directory is actually a knowledge base, probe with `iwe_stats` first. Few or zero documents means this skill does not apply; unload it rather than forcing the tools.
+
+## Orientation protocol (always start here)
+
+Never guess document keys. Orient first:
+
+1. `iwe_stats` — corpus size and shape. Cheap sanity check.
+2. `iwe_find(query="<topic>")` — fuzzy search for entry points. Use `roots` behavior via structural selectors when you want top-level topics only.
+3. `iwe_tree(key="<entry>", max_depth=2)` — see the hierarchy before reading bodies.
+4. `iwe_retrieve(key="<entry>", depth=1, context=1)` — read with structure.
+
+## Reading efficiently
+
+`iwe_retrieve` is the workhorse. Control cost explicitly:
+
+- `depth` — how many levels of included children to expand. Start at 1-2; increase only if needed.
+- `context` — parent levels to include, so you know where a document sits. `context=1` is usually enough.
+- `max_tokens` — ALWAYS set a budget (e.g. 2000-4000) on large corpora; results report truncation so you can drill further deliberately.
+- `exclude` — pass keys you have already read to avoid re-retrieving known content.
+- `links` / `backlinks` — include outbound/inbound references when tracing how a topic connects.
+
+Scope searches structurally with selectors on `iwe_find`/`iwe_retrieve`/`iwe_tree`:
+
+- `in` — only sub-documents of EVERY listed key (AND)
+- `in_any` — sub-documents of at least one key (OR)
+- `not_in` — exclude subtrees (e.g. archives)
+
+Filter by frontmatter with the YAML query language: `status: draft`, `created: {$gte: "2026-01-01"}`, `tags: {$in: [urgent]}`, `reviewed: {$exists: true}`.
+
+Use `iwe_squash(key=...)` to flatten a subtree into one linear document — good for producing a full plan readout or summary input.
+
+## Writing and refactoring
+
+Write tools: `iwe_create` (new doc from title + content), `iwe_update` (replace a doc's content), `iwe_delete` (remove + clean up references). Refactor tools: `iwe_rename` (key rename with automatic link updates everywhere), `iwe_extract` (split a section into its own doc, leaving an inclusion link), `iwe_inline` (merge a referenced doc back into its parent), `iwe_normalize` (reformat all docs consistently).
+
+Rules:
+
+- **Preview destructive operations**: `iwe_rename`, `iwe_delete`, `iwe_extract`, `iwe_inline`, and `iwe_normalize` support `dry_run` — use it first, show the user what will change, then apply.
+- Never rename or delete by editing files directly; the refactor tools update every referencing document, manual edits break links.
+- When adding a document, link it from an existing parent (inclusion link on its own line) so it joins the hierarchy instead of becoming an orphan.
+- Match the corpus conventions: check an existing document's frontmatter fields before inventing your own schema.
+- Do not run `iwe_normalize` across someone's knowledge base unprompted — it rewrites every file's formatting.
+
+## Anti-patterns
+
+- Retrieving with `depth=5` and no `max_tokens` "to get everything" — you will flood the context. Iterate: shallow first, drill selectively.
+- Calling `iwe_find` repeatedly with rephrased queries when structural navigation (`iwe_tree`, selectors) would locate the document deterministically.
+- Using IWE write tools on `.coyote/memory/` files — wrong tier; that corrupts the memory index.
+- Creating documents without linking them into the hierarchy — orphans are invisible to depth-based retrieval.

assets/skills/oracle-protocol/SKILL.md

@@ -0,0 +1,81 @@
+---
+description: Discipline for when and how to consult Oracle - blocking by design, never deliver an answer with Oracle pending, never bypass Oracle for design questions.
+---
+Oracle is your read-only, high-IQ advisor. Using it correctly is the difference between shipping the right thing slowly and shipping the wrong thing fast.
+
+## When you MUST consult Oracle
+
+Spawn `oracle` (do NOT answer yourself) any time the user asks:
+
+- "How should I..." / "What's the best way to..." — design/approach questions
+- "Why does X keep..." / "What's wrong with..." — complex debugging (not simple errors)
+- "Should I use X or Y?" — technology or pattern choices
+- "How should this be structured?" — architecture and organization
+- "Review this" / "What do you think of..." — code/design review
+- Tradeoff questions — performance vs readability, complexity vs flexibility
+- Multi-component questions — anything spanning 3+ files or modules
+- Vague/open-ended — "improve this", "make this better", "clean this up"
+- After 2+ failed fix attempts on the same problem — complex debugging
+
+Even if you think you know the answer, Oracle provides deeper, more thorough analysis. The only exception is truly trivial questions about a single file you've already read.
+
+## Oracle is BLOCKING by design
+
+The orchestrator (you) has paused work and CANNOT proceed until Oracle returns. This is intentional. The cost of Oracle's latency is paid so YOU get a thorough, considered answer rather than rushing in a wrong direction.
+
+Therefore:
+
+- **Do NOT implement before Oracle returns** if your implementation depends on Oracle's recommendation.
+- **Do NOT deliver the final user-facing answer** while Oracle is still running.
+- **Do NOT "time out and continue anyway"** for Oracle-dependent tasks.
+- While waiting, do only NON-OVERLAPPING prep work (work that doesn't depend on Oracle's verdict).
+
+## How to consult Oracle effectively
+
+Oracle has not seen the codebase or the conversation. Give it enough context to think:
+
+```
+## Question
+[The decision you need help with, stated as a question]
+
+## Background
+[Why this question matters now. What constraint or trigger raised it.]
+
+## Code context
+[Paste the actual snippets from prior exploration — file paths alone are not enough]
+- From `path/to/file.ext`:
+  <relevant 5-20 lines>
+
+## What you've considered
+[Options you've already weighed and their tradeoffs as you see them]
+
+## What I'd love Oracle to evaluate
+[Specific aspects: correctness, performance, security, future flexibility, etc.]
+```
+
+A well-scoped Oracle consult returns a tighter answer faster.
+
+## After Oracle returns
+
+1. Read the recommendation, reasoning, and risks sections carefully.
+2. If the recommendation conflicts with your prior plan, update the plan — do not silently ignore Oracle.
+3. Pass Oracle's recommendation (and reasoning) to the implementer (e.g., coder) as CONTEXT in your delegation.
+4. If you disagree with Oracle's verdict, raise it with the user before implementing the alternative — don't act unilaterally against Oracle's advice.
+
+## When NOT to consult Oracle
+
+- Simple file operations you can do with direct tools
+- First attempt at any fix (try yourself first; consult after 2 failures)
+- Questions answerable from code you've already read
+- Trivial decisions (variable names in small functions, formatting)
+- Things you can infer from existing code patterns
+
+Over-consultation wastes Oracle's budget and slows the work. Reserve Oracle for genuinely hard or load-bearing decisions.
+
+## Anti-patterns (BLOCKING)
+
+- Answering an architecture question yourself "just this once"
+- Delivering a user-facing answer while Oracle is still running
+- Implementing the obvious approach without consulting Oracle on a tradeoff question
+- Ignoring Oracle's recommendation because it's inconvenient
+- Polling `agent__collect` on a running Oracle (end your response, wait for notification)

assets/skills/parallel-research/SKILL.md

@@ -0,0 +1,70 @@
+---
+description: Fan-out exploration protocol — fire multiple research agents in parallel, wait for completion notifications, and never duplicate delegated work.
+---
+You are entering a research phase. Exploration is parallelizable; serial reads leave throughput on the table.
+
+## Fan out, don't read serially
+
+For any non-trivial codebase question, fire 2-5 `explore` agents in parallel, each scoped to a different angle:
+
+- Auth implementation? → one for routes, one for middleware, one for token handling, one for error response shape.
+- Bug investigation? → one for the failing path, one for similar working paths, one for recent changes near the area.
+
+Each agent gets a NARROW slice. Narrow scope = fast, focused result. Broad scope = the agent over-reads and returns a wall of text.
+
+## The wait protocol
+
+After spawning background agents:
+
+1. If you have **non-overlapping** work to do (work that doesn't depend on the delegated research), do it now.
+2. If you don't, **end your response.** Do not call `agent__collect` immediately — the agent is still running.
+3. The system notifies you when the agent completes (`pending_escalations` or completion event).
+4. On notification, call `agent__collect` to retrieve results.
+
+Polling `agent__collect` on a still-running agent blocks your turn for nothing.
+
+## Anti-duplication rule (BLOCKING)
+
+Once you delegate a search to an `explore` agent, **do not perform that same search yourself.**
+
+Forbidden:
+- After firing `explore` for "auth middleware", running `fs_grep` for "auth middleware" yourself
+- "Just quickly checking" the same files the delegate is checking
+- Re-doing the research while waiting impatiently
+
+Allowed:
+- Non-overlapping work in a different module
+- Preparation work that doesn't depend on the delegated result
+- Ending your response and waiting
+
+Duplicate searches waste tokens, may contradict the delegate, and defeat the point of parallelism.
+
+## Stop conditions
+
+Stop searching when:
+
+- The same information appears across multiple sources
+- Two search iterations yield no new useful data
+- A direct answer was found
+- You have enough context to proceed confidently
+
+Over-exploration is as bad as under-exploration. Time spent searching is time not spent shipping.
+
+## Parallel + sequential composition
+
+It is fine to fire `explore` and then `oracle` when oracle needs the explore results — just sequence them:
+
+1. Fire explore(s) in parallel.
+2. End response, wait for completion.
+3. Synthesize findings, fire `oracle` with those findings as CONTEXT.
+4. End response, wait for oracle.
+5. Act on oracle's recommendation.
+
+Don't fire oracle blind to "save a turn" — it will give worse advice.
+
+## Anti-patterns
+
+- One huge "explore everything about X" agent → slow, unfocused result
+- Serial explores ("wait for first, then fire next") → unnecessary latency
+- Firing 8+ parallel agents → diminishing returns, harder to synthesize
+- Calling `agent__collect` immediately after spawn → wastes a turn

assets/skills/plan-authoring/SKILL.md

@@ -0,0 +1,82 @@
+---
+description: Author executable high-level plans and per-step implementation plans for phased work. Defines the plan repo layout and step-plan schema. Grants filesystem access for grounding plans in real code.
+enabled_tools: fs_read, fs_grep, fs_glob, fs_ls, fs_cat, fs_write
+---
+You are writing implementation plans that a DIFFERENT agent will execute later, in a fresh session, with zero access to this conversation. The plan IS the executor's entire context. A plan that needs the conversation to make sense is a broken plan.
+
+## Plan repo layout
+
+Default layout (match the existing layout instead if the repo already has one):
+
+```
+plans/
+  plan.md            # high-level plan; links each step plan
+  steps/01-<slug>.md # one file per step, numbered in execution order
+  handoffs/          # written by executors; see `handoff-protocol`
+  NOTES.md           # rolling durable facts discovered during execution
+```
+
+In `plan.md`, link each step plan with an inclusion link (the link alone on its own line). This makes the plan repo an IWE hierarchy — agents navigating a large plan corpus can load `iwe-knowledge-base` and traverse it structurally instead of globbing.
+
+## High-level plan requirements
+
+- Ordered list of steps. Each step is independently implementable and independently verifiable — it compiles and its tests pass WITHOUT any later step existing.
+- The dependency graph is explicit and acyclic. If step 4 needs step 2's API, step 4's plan says so.
+- Steps are sized for one focused session: roughly 1-5 files of meaningful change. A step that needs "and then also..." is two steps.
+- State what the plan does NOT cover. Scope creep starts where scope boundaries are implicit.
+
+## Step plan schema
+
+Every step plan starts with frontmatter:
+
+```yaml
+---
+step: 3
+title: Add retry policy to the fetch client
+depends_on: [1, 2]
+status: pending   # pending | in-progress | complete
+---
+```
+
+And contains these sections, all mandatory:
+
+| Section | Contents |
+|---|---|
+| Objective | 1-3 sentences: what exists after this step that didn't before |
+| Context | File paths AND pasted code snippets (5-20 lines) showing the patterns to follow. Not just paths — actual code |
+| Tasks | Ordered, atomic tasks. Each maps to one todo item for the executor |
+| Acceptance criteria | Measurable behaviors. These become the tests |
+| Test commands | Exact commands to run, from the repo root |
+| Edge cases | Known edge cases this step must handle or explicitly punt on |
+| Out of scope | What the executor must NOT touch, even if tempting |
+
+## Writing for a context-free executor
+
+- Paste code snippets from your exploration into Context. "Follow the pattern in foo.rs" forces the executor to re-do exploration you already did.
+- Use repo-relative paths from the project root. Never "the file we discussed."
+- Name symbols exactly: `RetryPolicy::backoff`, not "the backoff logic."
+- If a decision was made in discussion (X over Y), record the decision AND the one-line reason. The executor will face the same fork and must not re-litigate it.
+- Write acceptance criteria as observable behavior ("returns 429 after 3 failed attempts"), not implementation ("uses a for loop"). Criteria that describe implementation produce tautological tests.
+
+## Grounding (before the plan is done)
+
+Plans rot when written from memory. Before finalizing each step plan:
+
+1. `fs_grep` every symbol the plan references — confirm it exists and is spelled right.
+2. `fs_read` the files listed in Context — confirm the pasted snippets are current.
+3. Confirm the test commands actually exist (check `justfile`, `Makefile`, `package.json` scripts, CI config).
+
+A plan referencing a function that doesn't exist fails the executor at the worst possible time: mid-implementation.
+
+## Edge cases are a first-class section
+
+For every step, enumerate the edge cases you can foresee: empty inputs, concurrent access, error paths, partial failures, migration/compat concerns. If an edge case belongs to a LATER step, write it in that step's plan now — not in a comment, not in your head. Executors are instructed to propagate newly discovered edge cases downstream; make their diff small by having the section exist.
+
+## Anti-patterns
+
+- "As discussed above" / "per our conversation" — the executor has no conversation
+- File paths without pasted snippets in Context — forces re-exploration
+- Acceptance criteria like "works correctly" — unmeasurable, untestable
+- A step that depends on a later step — cycle; re-order or merge
+- Omitting Out of scope — the executor will helpfully refactor things you didn't ask for
+- Frontmatter without `depends_on` or `status` — breaks status queries and dependency checks

assets/skills/plan-review/SKILL.md

@@ -0,0 +1,83 @@
+---
+description: Adversarial review of implementation plans against executability, verifiability, and completeness standards. Verdict is OKAY or REJECT with line-referenced complaints. Grants read-only filesystem access for ground-truth checks.
+enabled_tools: fs_read, fs_grep, fs_glob, fs_ls, fs_cat
+---
+You are reviewing an implementation plan BEFORE any code is written. You are the critic, not a co-author: your job is to find the ways this plan fails an executor who has zero conversation context, not to redesign the approach. A flaw caught here costs one plan edit; the same flaw caught mid-implementation costs a deviation, a handoff note, and possibly rework across steps.
+
+The plan schema you are checking against is defined in the `plan-authoring` skill — load it alongside this one if it is not already loaded.
+
+## Review checklist (in order)
+
+### 1. Executability without context
+
+Read the plan as if you know nothing but what is on the page.
+
+- Does every referenced decision carry its rationale, or does it assume a conversation you can't see?
+- Does Context contain pasted code snippets, or only file paths (which force re-exploration)?
+- Are symbols named exactly? "The validation logic" is not a name.
+
+### 2. Ground truth (verify, don't trust)
+
+Plans are written from exploration that may be stale or wrong. Spot-check claims against the actual codebase:
+
+- `fs_grep` for every function, type, and file the plan references. Flag anything that doesn't exist or is spelled differently.
+- `fs_read` 1-2 of the pasted Context snippets at their claimed locations. Flag drift.
+- Check that the Test commands exist (`justfile`, `Makefile`, `package.json`, CI config).
+
+A plan that references phantom code is an automatic REJECT.
+
+### 3. Verifiability
+
+- Is every acceptance criterion a measurable, observable behavior? "Works correctly" and "is robust" are unmeasurable — flag them.
+- Do the criteria describe behavior rather than implementation? Implementation-shaped criteria produce tautological tests.
+- Can each criterion be checked by the listed Test commands, or is there a criterion with no way to verify it?
+
+### 4. Dependencies and ordering
+
+- Is `depends_on` present, acyclic, and complete? If the step uses an API introduced in step N, is N listed?
+- Does anything in this step silently assume a LATER step's output? That's a cycle the frontmatter hides.
+- Is the step independently verifiable — will it build and pass tests without later steps existing?
+
+### 5. Scope and sizing
+
+- Is Out of scope present and specific? Absent scope boundaries invite helpful refactoring.
+- Is the step sized for one focused session (~1-5 files of meaningful change)? Flag steps hiding an "and then also".
+- Do two steps touch the same code region without an ordering constraint between them?
+
+### 6. Edge cases
+
+- Is the Edge cases section present and non-empty (or explicitly "none foreseen — <reason>")?
+- Think adversarially for 60 seconds: empty inputs, concurrency, error paths, partial failure, compat. Anything obvious the plan misses?
+- If this step creates a new surface (API, config, schema), do DOWNSTREAM step plans account for it where they must?
+
+## Verdict format
+
+End with exactly one of:
+
+```
+PLAN_REVIEW: OKAY
+<optional: 1-3 non-blocking observations>
+```
+
+```
+PLAN_REVIEW: REJECT
+Complaints:
+1. <file>:<line or section> — <what is wrong> — <what would fix it>
+2. ...
+```
+
+Every complaint must be actionable and point at a specific location. "The plan could be clearer" is noise; "steps/03-retry.md, Acceptance criteria #2 — 'handles errors gracefully' is unmeasurable — specify the expected behavior per error class" is signal.
+
+## Scope discipline
+
+- Review THE PLAN, not the design. If the approach is defensible, do not relitigate it because you'd have chosen differently. Flag design only when it is factually broken (races, missing dependency, contradicts the codebase).
+- Do not rewrite the plan yourself. Complaints, not patches — the author owns the fix.
+- Three strong complaints beat fifteen weak ones. If you have fifteen, the plan needs a rewrite, not a list: say so.
+
+## Anti-patterns
+
+- Approving without running a single ground-truth check — a syntax review, not a plan review
+- REJECT for style or phrasing while missing a phantom-symbol reference
+- Redesigning the author's approach in your complaints
+- Vague complaints with no location and no fix direction
+- Rubber-stamping a step with no acceptance criteria because "the tasks look reasonable"

assets/skills/step-implementation/SKILL.md

@@ -0,0 +1,85 @@
+---
+description: End-to-end protocol for executing one step of a phased implementation plan - orient, staleness check, checklist, implement, edge-case sweep, verify, review, handoff, approval. Grants shell access for build/test commands.
+enabled_tools: execute_command
+---
+You are executing ONE step of a phased implementation plan. Previous steps were executed in sessions you cannot see; later steps depend on what you do and document. The protocol below is ordered — do not skip phases, do not reorder them.
+
+Companion skills: load `handoff-protocol` before Phase 1 (you must READ a handoff correctly) and keep it loaded for Phase 8 (you must WRITE one). Load `verification-gates` for Phase 6. The plan schema is defined in `plan-authoring`.
+
+## Phase 1 - Orient
+
+1. Read the previous step's handoff (`plans/handoffs/`, highest step number below yours). If none exists, you are step 1.
+2. Read the current step plan (`plans/steps/`). Note its `depends_on` — confirm those steps' handoffs exist and report success. If a dependency failed or is missing, STOP and escalate via `user__ask`.
+3. Read `plans/NOTES.md` for durable facts discovered by earlier steps.
+4. Apply anything the previous handoff directed at your step (approved plan updates, warnings).
+5. Set the plan's frontmatter `status: in-progress`.
+
+## Phase 2 - Staleness check (BEFORE any edit)
+
+The plan was written before steps 1..N-1 changed the codebase. Verify its assumptions still hold:
+
+- Grep the symbols the plan references — do they still exist, with the claimed signatures?
+- Read the plan's Context snippets at their claimed locations — has the code drifted?
+- Confirm the Test commands still work.
+
+Discrepancies are deviations — handle them via Phase 5's protocol BEFORE implementing. Executing a stale plan literally is the primary failure mode of phased work.
+
+## Phase 3 - Checklist
+
+`todo__init` with the step objective, then one `todo__add` per task in the plan's Tasks section, in order. Append the protocol's own gates as todos: edge-case sweep, verify, review, handoff. Mark items done with `todo__done` as you go — never batch. The checklist is what survives context compression; keep it truthful.
+
+When you spawn an agent whose session you may need to resume, embed its session_id in the corresponding todo item text (`"Implement task 3 (coder ses_abc123)"`). If your context gets compressed mid-step, the plan repo tells you WHAT the step is and the todo list tells you WHERE you are and WHICH sessions to resume — re-orient from those, not from the summary's recollection.
+
+## Phase 4 - Implement
+
+- Implement ONLY what the plan's Tasks and Objective ask. Out of scope means out of scope.
+- Follow the patterns pasted in the plan's Context. When plan and current codebase disagree, the codebase wins — record the deviation.
+- Write tests from the plan's Acceptance criteria, not from your implementation. Criteria-first tests catch what tautological tests cannot.
+- While in the code, note (do not fix) anything the planning exploration missed — feed it to Phase 5.
+
+## Phase 5 - Edge-case sweep and deviations
+
+**Edge cases.** For each edge case you discovered: if it belongs to THIS step, handle it (or punt explicitly in the handoff with a reason). If it belongs to a LATER step, check that step's plan — if the plan already covers it, done; if not, add it to that plan's Edge cases section and record the addition in your handoff.
+
+**Deviations.** Classify each:
+
+| Class | Definition | Action |
+|---|---|---|
+| Minor | Same objective and scope, mechanics differ (renamed symbol, moved file, extra helper) | Resolve it, document in handoff |
+| Major | Changes scope, approach, interfaces, or invalidates a later step's assumptions | Do NOT silently proceed. Either escalate via `user__ask`, or write a proposed downstream-plan diff into the handoff per `handoff-protocol` |
+
+Never rewrite a later step's Objective, Tasks, or Out of scope directly — edge-case annotations are the only direct downstream edit you may make.
+
+## Phase 6 - Verify (order matters)
+
+1. Formatter (if configured) — format BEFORE collecting evidence, so evidence reflects final code.
+2. Linter (if configured) — fix findings your change introduced.
+3. Build/typecheck — exit code 0.
+4. FULL test suite — not just your new tests; regressions in untouched code are your problem if your change caused them.
+
+Capture commands and exit codes verbatim — they go in the handoff as evidence. Pre-existing failures: note explicitly, don't fix, don't hide. Apply the 3-strike rule: after 3 failed fix attempts, stop, revert to working state, escalate.
+
+## Phase 7 - Review
+
+Self-review the diff with `code-review` + `ai-slop-remover` loaded. For broad steps (5+ files or crossing architectural boundaries), request an independent pass (`code-reviewer` agent) instead. Fix blockers; re-run Phase 6 after any fix.
+
+## Phase 8 - Handoff
+
+Gate: every todo is either done or explicitly deferred with a reason. No silent drops.
+
+Write the handoff per `handoff-protocol` — schema, pasted evidence, deviations, downstream updates, notes for the next step. Append durable, step-independent facts to `plans/NOTES.md`. Set the plan's frontmatter `status: complete`.
+
+## Phase 9 - User approval
+
+Present: what was done, deviations, downstream plan changes (made or proposed), evidence summary, handoff location. Then STOP — do not begin the next step. If the user requests changes, address them, re-run Phase 6, update the handoff, and present again.
+
+## Anti-patterns
+
+- Editing code before the staleness check — the primary source of mid-step surprises
+- Implementing "while I'm here" improvements outside the plan's scope
+- Tests derived from the implementation instead of the acceptance criteria
+- Collecting build/test evidence BEFORE formatting/linting, then shipping different bytes
+- Running only your new tests and claiming "tests pass"
+- Silently absorbing a major deviation instead of escalating or proposing a plan diff
+- Rewriting downstream plan scope directly instead of proposing per `handoff-protocol`
+- Starting the next step without user approval

assets/skills/verification-gates/SKILL.md

@@ -0,0 +1,66 @@
+---
+description: Evidence requirements before claiming completion — diagnostics, build exit code, tests. No completion without proof. Grants shell access for running build/test commands.
+enabled_tools: execute_command
+---
+You are about to mark work complete. Before claiming "done," produce evidence. "I'm fairly confident it works" is not evidence.
+
+## Hard gates
+
+A task is NOT complete until:
+
+| Change kind | Required evidence |
+|---|---|
+| File edit | Read the file to confirm the change landed; output is clean (or only pre-existing issues, explicitly noted) |
+| Build command exists | `execute_command` the build; exit code 0 |
+| Test command exists | `execute_command` the tests; pass (or explicit note of pre-existing failures unrelated to this change) |
+| Delegation | The delegate's result was received AND verified against your acceptance criteria |
+
+**No evidence = not complete.** Marking a todo done without evidence is dishonest reporting.
+
+## The verification loop
+
+After every meaningful edit:
+
+1. Read the changed file region (confirm the change actually landed where intended).
+2. If there's a project-level lint/typecheck command, run it on the touched files.
+3. Run the project's build/check command if one exists.
+4. Run the project's test command if one exists.
+5. Only then mark the corresponding todo `completed`.
+
+If any step fails: do not mark complete. Fix the issue or surface it explicitly.
+
+## Build/test detection (fallback)
+
+If no build/test command is configured, try standard ones for the project:
+
+- Rust: `cargo check`, `cargo test`
+- Node/TS: `npm run build`, `npm test`, or `pnpm` / `yarn` equivalents
+- Python: `pytest`, `python -m mypy <pkg>`, `ruff check`
+- Go: `go build ./...`, `go test ./...`
+
+Run from the project root. Capture exit codes.
+
+## Distinguishing your failures from pre-existing failures
+
+If build or tests fail, identify the cause:
+
+- Caused by your change? → fix it before reporting complete.
+- Pre-existing (unrelated)? → note it explicitly: "Done. Build passes. Note: 3 lint errors pre-existing in unrelated files, not touched."
+
+Never silently leave broken state behind. Never delete a failing test to make CI green.
+
+## Anti-patterns (BLOCKING)
+
+- "It should work" without running anything
+- Marking a todo complete based on intent, not verified outcome
+- Suppressing errors with `@ts-ignore`, `as any`, `#[allow(...)]` on unfamiliar lints, empty catch blocks
+- Deleting failing tests to "pass"
+- Reporting "all green" when you only ran a subset
+
+## Reporting completion
+
+When the work is verifiably done, report in one sentence:
+
+> "Done. Build passes, 47 tests pass. Modified `auth.rs:42-58` to add JWT validation."
+
+Not a paragraph. Not a victory lap. Specific, terse, evidence-backed.

config.agent.example.yaml

@@ -1,5 +1,5 @@
 # Agent-specific configuration
-# Location `<loki-config-dir>/agents/<agent-name>/config.yaml`
+# Location `<coyote-config-dir>/agents/<agent-name>/config.yaml`
 #
 # Available Environment Variables:
 #   - <agent-name>_MODEL
@@ -21,14 +21,14 @@ version: 1                       # Version of the agent
 # The auto-continue system provides built-in task tracking for improved reliability.
 # When enabled, the model can create todo lists and the system will automatically
 # prompt it to continue when incomplete tasks remain.
-# See the [Todo System documentation](https://github.com/Dark-Alex-17/loki/wiki/TODO-System) for more information
+# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
 auto_continue: false             # Enable automatic continuation when incomplete todos remain
 max_auto_continues: 10           # Maximum number of automatic continuations before stopping
 inject_todo_instructions: true   # Inject the default todo tool usage instructions into the agent's system prompt
 continuation_prompt: null        # Custom prompt used when auto-continuing (optional; uses default if null)
 # Sub-Agent Spawning System
 # Enable this agent to spawn and manage child agents in parallel.
-# See https://github.com/Dark-Alex-17/loki/wiki/Agents for detailed documentation.
+# See https://github.com/Dark-Alex-17/coyote/wiki/Agents for detailed documentation.
 can_spawn_agents: false          # Enable the agent to spawn child agents
 max_concurrent_agents: 4         # Maximum number of agents that can run simultaneously
 max_agent_depth: 3               # Maximum nesting depth for sub-agents (prevents runaway spawning)
@@ -37,11 +37,23 @@ summarization_model: null        # Model to use for summarizing sub-agent output
 summarization_threshold: 4000    # Character threshold above which sub-agent output is summarized before returning to parent
 escalation_timeout: 300          # Seconds a sub-agent waits for a user interaction response before timing out (default: 5 minutes)
 mcp_servers:                     # Optional list of MCP servers that the agent utilizes
-  - github                       # Corresponds to the name of an MCP server in the `<loki-config-dir>/functions/mcp.json` file
+  - github                       # Corresponds to the name of an MCP server in the `<coyote-config-dir>/functions/mcp.json` file
 global_tools:                    # Optional list of additional global tools to enable for the agent; i.e. not tools specific to the agent
   - web_search
   - fs
   - python
+skills_enabled: true             # Master switch for skills in this agent (default: inherit from global).
+                                 # Skills also require `function_calling_support: true` in the global config.
+enabled_skills:                  # Optional list of skills available when this agent runs.
+                                 # Must be a subset of global `visible_skills`. Omit to inherit the global default.
+  - git-master
+  - ai-slop-remover
+inject_skill_instructions: true  # Inject a short hint pointing the model at `skill__list` when skills are enabled
+                                 # (default: true). Suppressed automatically when no skills are available.
+skill_instructions: null         # Custom text for the skill hint (optional; uses built-in default if null)
+memory: null                     # Per-agent memory override (default: inherit). Set to `false` to disable memory
+                                 # for this agent regardless of workspace/global presence. See the Memory wiki page.
+
 dynamic_instructions: false      # Whether to use dynamic instructions for the agent; if false, static instructions are used
 instructions: |                  # Static instructions for the agent; ignored if dynamic instructions are used
   You are a AI agent designed to demonstrate agent capabilities.
@@ -80,10 +92,10 @@ conversation_starters:          # Optional conversation starters for the agent
   - What is the best way to exercise?
   - How do I manage my time effectively?
 documents:                     # Optional documents to load for the agent
-  - git:/some/repo             # Explicitly tell Loki to use the 'git' document loader using an absolute path
+  - git:/some/repo             # Explicitly tell Coyote to use the 'git' document loader using an absolute path
-  - pdf:some-pdf-file.pdf      # Explicitly tell Loki to use the 'pdf' document loader using a relative path
+  - pdf:some-pdf-file.pdf      # Explicitly tell Coyote to use the 'pdf' document loader using a relative path
   - https://some-website.com/some-page
-  - some-file.pdf              # File with relative path to the <loki-config-dir>/agents/<agent-name> directory; i.e. file in the same directory as this config file
+  - some-file.pdf              # File with relative path to the <coyote-config-dir>/agents/<agent-name> directory; i.e. file in the same directory as this config file
   - ~/some-file.txt            # File in the user's home directory
   - /absolute/path/to/some-file.md  # File with absolute path
   - /absolute/path/**/NAME.txt    # Find all NAME.txt files in the specified directory and all its subdirectories

config.example.yaml

@@ -18,32 +18,80 @@ agent_session: null              # Set a session to use when starting an agent (
 
 # ---- Appearance ----
 highlight: true                  # Controls syntax highlighting
-light_theme: false               # Activates a light color theme when true. env: LOKI_LIGHT_THEME
+light_theme: false               # Activates a light color theme when true. env: COYOTE_LIGHT_THEME
 
 # ---- Miscellaneous ----
-user_agent: null                 # Set User-Agent HTTP header, use `auto` for loki/<current-version>
+user_agent: null                 # Set User-Agent HTTP header, use `auto` for coyote/<current-version>
 save_shell_history: true         # Whether to save shell execution command to the history file
 sync_models_url: >               # URL to sync model changes from
-  https://raw.githubusercontent.com/Dark-Alex-17/loki/refs/heads/main/models.yaml
+  https://raw.githubusercontent.com/Dark-Alex-17/coyote/refs/heads/main/models.yaml
 
 # ---- REPL Prompt ----
-# Custom REPL left/right prompts; see the [REPL Prompt Documentation](https://github.com/Dark-Alex-17/loki/wiki/REPL-Prompt) for more information
+# Custom REPL left/right prompts; see the [REPL Prompt Documentation](https://github.com/Dark-Alex-17/coyote/wiki/REPL-Prompt) for more information
 left_prompt:
   '{color.red}{model}){color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
 right_prompt:
   '{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'
 
 # ---- Vault ----
-# See the [Vault documentation](https://github.com/Dark-Alex-17/loki/wiki/Vault) for more information on the Loki vault
+# See the [Vault documentation](https://github.com/Dark-Alex-17/coyote/wiki/Vault) for more information on the Coyote vault.
-vault_password_file: null        # Path to a file containing the password for the Loki vault (cannot be a secret template)
+#
+# The secrets_provider tells Coyote where to read and write secrets referenced via {{SECRET_NAME}} syntax.
+#
+# Shorthand: set vault_password_file to enable the local provider with that password file.
+vault_password_file: null        # Path to a file containing the password for the Coyote vault (cannot be a secret template)
+#
+# Explicit: set secrets_provider to one of the supported types below. When secrets_provider is set,
+# vault_password_file is ignored. Note: secrets_provider itself cannot use {{SECRET}} template syntax.
+# The vault must be initialized before any secrets can be resolved.
+#
+# Local (same as the shorthand above):
+# secrets_provider:
+#   type: local
+#   password_file: ~/.coyote_password
+#
+# AWS Secrets Manager (requires an authenticated AWS CLI; see `aws sso login` or `aws configure`):
+# secrets_provider:
+#   type: aws_secrets_manager
+#   aws_profile: default
+#   aws_region: us-east-1
+#
+# GCP Secret Manager (requires `gcloud auth application-default login`):
+# secrets_provider:
+#   type: gcp_secret_manager
+#   gcp_project_id: my-project-id
+#
+# Azure Key Vault (requires `az login`):
+# secrets_provider:
+#   type: azure_key_vault
+#   vault_name: my-vault-name
+#
+# gopass (requires the `gopass` CLI to be installed and initialized):
+# secrets_provider:
+#   type: gopass
+#   store: my-store              # Optional; omit to use the default store
+#
+# 1Password (requires the `op` CLI to be installed and signed in via `op signin`):
+# secrets_provider:
+#   type: one_password
+#   vault: Production            # Optional; omit to use the default vault
+#   account: my.1password.com    # Optional; omit to use the default account
 
 # ---- Function Calling ----
-# See the [Tools documentation](https://github.com/Dark-Alex-17/loki/wiki/Tools) for more details
+# See the [Tools documentation](https://github.com/Dark-Alex-17/coyote/wiki/Tools) for more details
-function_calling: true           # Enables or disables function calling (Globally).
+function_calling_support: true           # Enables or disables function calling (Globally).
 mapping_tools:                   # Alias for a tool or toolset
   fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write,fs_read,fs_glob,fs_grep'
-enabled_tools: null              # Which tools to enable by default. (e.g. 'fs,web_search_loki')
+enabled_tools: null              # Which tools to enable by default.
+                                 # Accepts either a YAML list or a comma-separated string. Use 'all' to enable everything.
+                                 # Example (list form):
+                                 #   enabled_tools:
+                                 #     - fs
+                                 #     - web_search_coyote
+                                 # Example (comma-separated form):
+                                 #   enabled_tools: fs,web_search_coyote
 visible_tools:                   # Which tools are visible to be compiled (and are thus able to be defined in 'enabled_tools')
+#  - ast_grep.sh
 #  - demo_py.py
 #  - demo_sh.sh
 #  - demo_ts.ts
@@ -69,29 +117,59 @@ visible_tools:                   # Which tools are visible to be compiled (and a
 #  - search_wolframalpha.sh
 #  - send_mail.sh
 #  - send_twilio.sh
-#  - web_search_loki.sh
+#  - web_search_coyote.sh
 #  - web_search_perplexity.sh
 #  - web_search_tavily.sh
 
 # ---- MCP Servers ----
-# See the [MCP Servers documentation](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers) for more details
+# See the [MCP Servers documentation](https://github.com/Dark-Alex-17/coyote/wiki/MCP-Servers) for more details
 mcp_server_support: true         # Enables or disables MCP servers (globally).
 mapping_mcp_servers:             # Alias for an MCP server or set of servers
   git: github,gitmcp
-enabled_mcp_servers: null        # Which MCP servers to enable by default (e.g. 'github,slack,ddg-search')
+enabled_mcp_servers: null        # Which MCP servers to enable by default.
+                                 # Accepts either a YAML list or a comma-separated string. Use 'all' to enable everything.
+                                 # Example (list form):
+                                 #   enabled_mcp_servers:
+                                 #     - github
+                                 #     - slack
+                                 # Example (comma-separated form):
+                                 #   enabled_mcp_servers: github,slack,ddg-search
+
+# ---- Skills ----
+# Skills are modular knowledge or capability packs the LLM can load and unload mid-conversation.
+# See the [Skills documentation](https://github.com/Dark-Alex-17/coyote/wiki/Skills) for more details.
+skills_enabled: true              # Master switch. Set to false to hide all skill management tools from the model.
+                                  # Skills also require `function_calling_support: true` above to work at all.
+visible_skills:                   # The universe of skills allowed to be enabled in any context. Omit (null) for "all installed".
+  - ai-slop-remover
+  - code-review
+  - frontend-ui-ux
+  - git-master
+enabled_skills: null              # Which skills are available by default (no role/agent/session active). null = all visible.
+                                  # Accepts either a YAML list or a comma-separated string.
+                                  # Example (list form):
+                                  #   enabled_skills:
+                                  #     - git-master
+                                  #     - ai-slop-remover
+                                  # Example (comma-separated form):
+                                  #   enabled_skills: git-master,ai-slop-remover
+inject_skill_instructions: true   # Inject a short hint pointing the model at `skill__list` when skills are enabled in
+                                  # this context. Only injected if `function_calling_support`, `skills_enabled`, and the
+                                  # effective enabled skill set is non-empty (default: true).
+skill_instructions: null          # Custom text used for the skill hint when injected. If null, uses built-in default.
 
 # ---- Auto-Continue (Todo System) ----
 # The auto-continue system provides built-in task tracking for improved reliability.
 # When enabled, the model can create todo lists and the system will automatically
 # prompt it to continue when incomplete tasks remain.
-# See the [Todo System documentation](https://github.com/Dark-Alex-17/loki/wiki/TODO-System) for more information
+# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
 auto_continue: false              # Enable automatic continuation when incomplete todos remain (default: false)
 max_auto_continues: 10            # Maximum number of automatic continuations before stopping (default: 10)
 inject_todo_instructions: true    # Inject default todo usage instructions into the system prompt (default: true)
 continuation_prompt: null         # Custom prompt used when auto-continuing. If null, uses built-in default
 
 # ---- Session ----
-# See the [Session documentation](https://github.com/Dark-Alex-17/loki/wiki/Sessions) for more information
+# See the [Session documentation](https://github.com/Dark-Alex-17/coyote/wiki/Sessions) for more information
 save_session: null               # Controls the persistence of the session. If true, auto save; if false, don't auto-save save; if null, ask the user what to do
 compression_threshold: 4000      # Compress the session when the token count reaches or exceeds this threshold
 summarization_prompt: >          # The text prompt used for creating a concise summary of session message
@@ -99,10 +177,23 @@ summarization_prompt: >          # The text prompt used for creating a concise s
 summary_context_prompt: >        # The text prompt used for including the summary of the entire session as context to the model
   'This is a summary of the chat history as a recap: '
 
+# ---- Memory ----
+# See the [Memory documentation](https://github.com/Dark-Alex-17/coyote/wiki/Memory) for more information.
+# Memory is opt-in by workspace presence (a `COYOTE.md` or `.coyote/memory/MEMORY.md`)
+# and global presence (`<config_dir>/memory/MEMORY.md`). Set `memory: false` to disable
+# even when memory files exist. The cascade is: agent > session > role > app.
+# Bootstrap with `coyote --init-memory [global|workspace]` to create the marker file
+# the LLM needs before it will write any memory.
+memory: null                     # null = enabled when memory exists on disk; true = force on; false = force off
+memory_cap_with_tools: null      # Char cap for injected memory when function calling is available (default: 6000).
+                                 # Only MEMORY.md indexes are injected; the LLM uses memory__read to fetch drill files.
+memory_cap_without_tools: null   # Char cap when function calling is unavailable (default: 12000).
+                                 # Indexes plus drill file bodies are injected up to this cap.
+
 # ---- RAG ----
-# See the [RAG Docs](https://github.com/Dark-Alex-17/loki/wiki/RAG) for more details.
+# See the [RAG Docs](https://github.com/Dark-Alex-17/coyote/wiki/RAG) for more details.
 rag_embedding_model: null        # Specifies the embedding model used for context retrieval
-rag_reranker_model: null         # Specifies the reranker model used for sorting retrieved documents; Loki uses Reciprocal Rank Fusion by default
+rag_reranker_model: null         # Specifies the reranker model used for sorting retrieved documents; Coyote uses Reciprocal Rank Fusion by default
 rag_top_k: 5                     # Specifies the number of documents to retrieve for answering queries
 rag_chunk_size: null             # Defines the size of chunks for document processing in characters
 rag_chunk_overlap: null          # Defines the overlap between chunks
@@ -141,12 +232,12 @@ document_loaders:
   docx: 'pandoc --to plain $1'                                                          # Use pandoc to convert a .docx file to text
   # (see https://pandoc.org for details on how to install pandoc)
   jina: 'curl -fsSL https://r.jina.ai/$1 -H "Authorization: Bearer {{JINA_API_KEY}}'    # Use Jina to translate a website into text;
-  # Requires a Jina API key to be added to the Loki vault
+  # Requires a Jina API key to be added to the Coyote vault
   git: >                                                                                # Use yek to load a git repository into the knowledgebase (https://github.com/bodo-run/yek)
     sh -c "yek $1 --json | jq 'map({ path: .filename, contents: .content })'"
 
 # ---- Clients ----
-# See the [Clients documentation](https://github.com/Dark-Alex-17/loki/wiki/Clients) for more details
+# See the [Clients documentation](https://github.com/Dark-Alex-17/coyote/wiki/Clients) for more details
 clients:
   # All clients have the following configuration:
   # - type: xxxx
@@ -177,14 +268,14 @@ clients:
   # See https://platform.openai.com/docs/quickstart
   - type: openai
     api_base: https://api.openai.com/v1               # Optional
-    api_key: '{{OPENAI_API_KEY}}'                     # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{OPENAI_API_KEY}}'                     # You can either hard-code or inject secrets from the Coyote vault
     organization_id: org-xxx                          # Optional
 
   # For any platform compatible with OpenAI's API
   - type: openai-compatible
     name: ollama
     api_base: http://localhost:11434/v1
-    api_key: '{{OLLAMA_API_KEY}}'                     # Optional; You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{OLLAMA_API_KEY}}'                     # Optional; You can either hard-code or inject secrets from the Coyote vault
     models:
       - name: deepseek-r1
         max_input_tokens: 131072
@@ -202,9 +293,9 @@ clients:
   # See https://ai.google.dev/docs
   - type: gemini
     api_base: https://generativelanguage.googleapis.com/v1beta
-    api_key: '{{GEMINI_API_KEY}}'                       # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{GEMINI_API_KEY}}'                       # You can either hard-code or inject secrets from the Coyote vault
-    auth: null                                          # When set to 'oauth', Loki will use OAuth instead of an API key
+    auth: null                                          # When set to 'oauth', Coyote will use OAuth instead of an API key
-                                                        # Authenticate with `loki --authenticate` or `.authenticate` in the REPL
+                                                        # Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
     patch:
       chat_completions:
         '.*':
@@ -222,49 +313,49 @@ clients:
   # See https://docs.anthropic.com/claude/reference/getting-started-with-the-api
   - type: claude
     api_base: https://api.anthropic.com/v1              # Optional
-    api_key: '{{ANTHROPIC_API_KEY}}'                    # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{ANTHROPIC_API_KEY}}'                    # You can either hard-code or inject secrets from the Coyote vault
-    auth: null                                          # When set to 'oauth', Loki will use OAuth instead of an API key
+    auth: null                                          # When set to 'oauth', Coyote will use OAuth instead of an API key
-                                                        # Authenticate with `loki --authenticate` or `.authenticate` in the REPL
+                                                        # Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
 
   # See https://docs.mistral.ai/
   - type: openai-compatible
     name: mistral
     api_base: https://api.mistral.ai/v1
-    api_key: '{{MISTRAL_API_KEY}}'                      # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{MISTRAL_API_KEY}}'                      # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://docs.x.ai/docs
   - type: openai-compatible
     name: xai
     api_base: https://api.x.ai/v1
-    api_key: '{{XAI_API_KEY}}'                          # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{XAI_API_KEY}}'                          # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://docs.ai21.com/docs/overview
   - type: openai-compatible
     name: ai12
     api_base: https://api.ai21.com/studio/v1
-    api_key: '{{AI21_API_KEY}}'                         # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{AI21_API_KEY}}'                         # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://docs.cohere.com/docs/the-cohere-platform
   - type: cohere
     api_base: https://api.cohere.ai/v2                  # Optional
-    api_key: '{{COHERE_API_KEY}}'                       # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{COHERE_API_KEY}}'                       # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://docs.perplexity.ai/getting-started/overview
   - type: openai-compatible
     name: perplexity
     api_base: https://api.perplexity.ai
-    api_key: '{{PERPLEXITY_API_KEY}}'                   # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{PERPLEXITY_API_KEY}}'                   # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://console.groq.com/docs/quickstart
   - type: openai-compatible
     name: groq
     api_base: https://api.groq.com/openai/v1
-    api_key: '{{GROQ_API_KEY}}'                         # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{GROQ_API_KEY}}'                         # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart
   - type: azure-openai
     api_base: https://{RESOURCE}.openai.azure.com
-    api_key: '{{AZURE_OPENAI_API_KEY}}'                 # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{AZURE_OPENAI_API_KEY}}'                 # You can either hard-code or inject secrets from the Coyote vault
     models:
       - name: gpt-4o                                    # Model deployment name
         max_input_tokens: 128000
@@ -295,8 +386,8 @@ clients:
 
   # See https://docs.aws.amazon.com/bedrock/latest/userguide/
   - type: bedrock
-    access_key_id: '{{AWS_ACCESS_KEY_ID}}'              # You can either hard-code or inject secrets from the Loki vault
+    access_key_id: '{{AWS_ACCESS_KEY_ID}}'              # You can either hard-code or inject secrets from the Coyote vault
-    secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}'      # You can either hard-code or inject secrets from the Loki vault
+    secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}'      # You can either hard-code or inject secrets from the Coyote vault
     region: xxx
     session_token: xxx                                  # Optional, only needed for temporary credentials
 
@@ -304,67 +395,67 @@ clients:
   - type: openai-compatible
     name: cloudflare
     api_base: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1
-    api_key: '{{CLOUDFLARE_API_KEY}}'                    # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{CLOUDFLARE_API_KEY}}'                    # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
   - type: openai-compatible
     name: ernie
     api_base: https://qianfan.baidubce.com/v2
-    api_key: '{{BAIDU_API_KEY}}'                        # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{BAIDU_API_KEY}}'                        # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://dashscope.aliyun.com/
   - type: openai-compatible
     name: qianwen
     api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
-    api_key: '{{ALIYUN_API_KEY}}'                       # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{ALIYUN_API_KEY}}'                       # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://cloud.tencent.com/product/hunyuan
   - type: openai-compatible
     name: hunyuan
     api_base: https://api.hunyuan.cloud.tencent.com/v1
-    api_key: '{{TENCENT_API_KEY}}'                      # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{TENCENT_API_KEY}}'                      # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://platform.moonshot.cn/docs/intro
   - type: openai-compatible
     name: moonshot
     api_base: https://api.moonshot.cn/v1
-    api_key: '{{MOONSHOT_API_KEY}}'                     # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{MOONSHOT_API_KEY}}'                     # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://platform.deepseek.com/api-docs/
   - type: openai-compatible
     name: deepseek
     api_base: https://api.deepseek.com
-    api_key: '{{DEEPSEEK_API_KEY}}'                     # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{DEEPSEEK_API_KEY}}'                     # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://open.bigmodel.cn/dev/howuse/introduction
   - type: openai-compatible
     name: zhipuai
     api_base: https://open.bigmodel.cn/api/paas/v4
-    api_key: '{{ZHIPUAI_API_KEY}}'                      # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{ZHIPUAI_API_KEY}}'                      # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://platform.minimaxi.com/document/Fast%20access
   - type: openai-compatible
     name: minimax
     api_base: https://api.minimax.chat/v1
-    api_key: '{{MINIMAX_API_KEY}}'                      # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{MINIMAX_API_KEY}}'                      # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://openrouter.ai/docs#quick-start
   - type: openai-compatible
     name: openrouter
     api_base: https://openrouter.ai/api/v1
-    api_key: '{{OPENROUTER_API_KEY}}'                   # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{OPENROUTER_API_KEY}}'                   # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://github.com/marketplace/models
   - type: openai-compatible
     name: github
     api_base: https://models.inference.ai.azure.com
-    api_key: '{{GITHUB_API_KEY}}'                       # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{GITHUB_API_KEY}}'                       # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://deepinfra.com/docs
   - type: openai-compatible
     name: deepinfra
     api_base: https://api.deepinfra.com/v1/openai
-    api_key: '{{DEEPINFRA_API_KEY}}'                    # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{DEEPINFRA_API_KEY}}'                    # You can either hard-code or inject secrets from the Coyote vault
 
 
   # ----- RAG dedicated -----
@@ -373,10 +464,10 @@ clients:
   - type: openai-compatible
     name: jina
     api_base: https://api.jina.ai/v1
-    api_key: '{{JINA_API_KEY}}'                         # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{JINA_API_KEY}}'                         # You can either hard-code or inject secrets from the Coyote vault
 
   # See https://docs.voyageai.com/docs/introduction
   - type: openai-compatible
     name: voyageai
     api_base: https://api.voyageai.com/v1
-    api_key: '{{VOYAGEAI_API_KEY}}'                     # You can either hard-code or inject secrets from the Loki vault
+    api_key: '{{VOYAGEAI_API_KEY}}'                     # You can either hard-code or inject secrets from the Coyote vault

config.role.example.md

@@ -8,15 +8,30 @@ name: <role-name>                     # The name of the role
 model: openai:gpt-4o                  # The model to use for this role
 temperature: 0.2                      # The temperature to use for this role when querying the model
 top_p: 0                              # The top_p to use for this role when querying the model
-enabled_tools: fs_ls,fs_cat           # A comma-separated list of tools to enable for this role
+enabled_tools:                        # Tools to enable for this role. Accepts a YAML list (preferred)
-enabled_mcp_servers: github,gitmcp    # A comma-separated list of MCP servers to enable for this role
+  - fs_ls                             # or a comma-separated string (e.g. `enabled_tools: fs_ls,fs_cat`).
+  - fs_cat                            # Use `all` to enable every visible tool.
+enabled_mcp_servers:                  # MCP servers to enable for this role. Accepts a YAML list (preferred)
+  - github                            # or a comma-separated string (e.g. `enabled_mcp_servers: github,gitmcp`).
+  - gitmcp                            # Use `all` to enable every configured MCP server.
+skills_enabled: true                  # Master switch for skills in this role (default: inherit from global).
+                                      # Skills also require `function_calling_support: true` in the global config.
+enabled_skills:                       # Skills available when this role is active. Accepts a YAML list (preferred)
+  - git-master                        # or a comma-separated string (e.g. `enabled_skills: git-master,ai-slop-remover`).
+  - ai-slop-remover                   # Must be a subset of global `visible_skills`. Omit to inherit the global default.
+inject_skill_instructions: true       # Inject a short hint pointing the model at `skill__list` when skills are enabled 
+                                      # (default: true). Suppressed automatically when no skills are available.
+skill_instructions: null              # Custom text for the skill hint (optional; uses built-in default if null)
+memory: null                          # Per-role memory override (default: inherit). Set to `false` to disable memory
+                                      # when this role is active. See the Memory wiki page.
+
 prompt: null                          # A custom prompt to use for this role that will immediately query
                                       # the model for output instead of using the instructions below
 # Auto-Continue (Todo System)
 # The auto-continue system provides built-in task tracking for improved reliability.
 # When enabled, the model can create todo lists and the system will automatically
 # prompt it to continue when incomplete tasks remain.
-# See the [Todo System documentation](https://github.com/Dark-Alex-17/loki/wiki/TODO-System) for more information
+# See the [Todo System documentation](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System) for more information
 auto_continue: false                  # Enable automatic continuation when incomplete todos remain (default: false)
 max_auto_continues: 10                # Maximum number of automatic continuations before stopping (default: 10)
 inject_todo_instructions: true        # Inject default todo tool usage instructions into the system prompt (default: true)

deployment/homebrew/coyote.rb.template

@@ -0,0 +1,23 @@
+# Documentation: https://docs.brew.sh/Formula-Cookbook
+#                https://rubydoc.brew.sh/Formula
+class Coyote < Formula
+  desc "All-in-one, batteries included LLM CLI tool"
+  homepage "https://github.com/Dark-Alex-17/coyote"
+  if OS.mac? and Hardware::CPU.arm?
+    url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-aarch64-apple-darwin.tar.gz"
+    sha256 "$hash_mac_arm"
+  elsif OS.mac? and Hardware::CPU.intel?
+    url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-x86_64-apple-darwin.tar.gz"
+    sha256 "$hash_mac"
+  else
+    url "https://github.com/Dark-Alex-17/coyote/releases/download/v$version/coyote-x86_64-unknown-linux-musl.tar.gz"
+    sha256 "$hash_linux"
+  end
+  version "$version"
+  license "MIT"
+
+  def install
+    bin.install "coyote"
+    ohai "You're done! Get started with \"coyote --help\""
+  end
+end

deployment/homebrew/loki.rb.template

@@ -1,23 +0,0 @@
-# Documentation: https://docs.brew.sh/Formula-Cookbook
-#                https://rubydoc.brew.sh/Formula
-class Loki < Formula
-  desc "All-in-one, batteries included LLM CLI tool"
-  homepage "https://github.com/Dark-Alex-17/loki"
-  if OS.mac? and Hardware::CPU.arm?
-    url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-aarch64-apple-darwin.tar.gz"
-    sha256 "$hash_mac_arm"
-  elsif OS.mac? and Hardware::CPU.intel?
-    url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-x86_64-apple-darwin.tar.gz"
-    sha256 "$hash_mac"
-  else
-    url "https://github.com/Dark-Alex-17/loki/releases/download/v$version/loki-x86_64-unknown-linux-musl.tar.gz"
-    sha256 "$hash_linux"
-  end
-  version "$version"
-  license "MIT"
-
-  def install
-    bin.install "loki"
-    ohai "You're done! Get started with \"loki --help\""
-  end
-end

graph.example.yaml

@@ -1,5 +1,5 @@
 # Graph-based agent definition (full-featured reference)
-# Location: <loki-config-dir>/agents/<agent-name>/graph.yaml
+# Location: <coyote-config-dir>/agents/<agent-name>/graph.yaml
 #
 # A graph agent is defined by this file alone. An agent directory contains
 # either a config.yaml (a normal LLM-loop agent) or a graph.yaml (a graph
@@ -13,7 +13,7 @@
 # runnable deep-research graph agent, see assets/agents/deep-research/.
 #
 # Full documentation:
-#   https://github.com/Dark-Alex-17/loki/wiki/Graph-Agents
+#   https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents
 
 # ---------------------------------------------------------------------------
 # Identity
@@ -35,12 +35,38 @@ temperature: 0.0                   # Default sampling temperature for `llm` node
 top_p: null                        # Default sampling top-p for `llm` nodes
 
 global_tools:                      # Tool universe an `llm` node's `tools:` whitelist draws from
-  - web_search_loki.sh
+  - web_search_coyote.sh
   - fetch_url_via_curl.sh
 
 mcp_servers:                       # MCP servers an `llm` node may reference via `mcp:<server>`
   - ddg-search
 
+# ---------------------------------------------------------------------------
+# Skills policy (optional)
+# Skills only attach to `llm` nodes inside a graph. Both fields are optional.
+#
+#   skills_enabled:  master switch for skills across every `llm` node in the
+#                    graph. false here turns skills off entirely, regardless of
+#                    per-node settings. Omitting it inherits the agent / global
+#                    cascade (default true).
+#   enabled_skills:  the *universe* of skill names any `llm` node in this graph
+#                    may reference in its own `enabled_skills`. The validator
+#                    rejects per-node entries outside this list at load time.
+#                    Omit to inherit the agent / global cascade.
+#
+# Per-node usage is documented on the `triage` llm node below. There is no
+# auto-load: the model uses `skill__list` / `skill__load` / `skill__unload` to
+# bring skills in as it needs them, exactly like in normal-agent contexts.
+# ---------------------------------------------------------------------------
+skills_enabled: true
+enabled_skills:
+  - code-review
+  - git-master
+  - ai-slop-remover
+inject_skill_instructions: true   # Inject a hint pointing the model at `skill__list`. Defaults to true; suppressed
+                                  # automatically when no skills are available.
+skill_instructions: null          # Custom text for the skill hint (optional; uses the built-in default if omitted).
+
 conversation_starters:             # Suggested prompts surfaced in the UI
   - "Research the current state of WebAssembly outside the browser"
 
@@ -52,7 +78,7 @@ conversation_starters:             # Suggested prompts surfaced in the UI
 #     (see initial_state below).
 #   - Script nodes via the env var `LLM_AGENT_VAR_<UPPER_NAME>`.
 # Values may be overridden at runtime with
-#   `loki -a <agent> --agent-variable <name> <value> "..."`.
+#   `coyote -a <agent> --agent-variable <name> <value> "..."`.
 # ---------------------------------------------------------------------------
 variables:
   - name: project_dir
@@ -103,7 +129,7 @@ reducers:
 # Values placed into graph state before any node runs; reference anywhere via
 # {{key}}.
 #
-# Note: `initial_prompt` is seeded automatically by Loki with the
+# Note: `initial_prompt` is seeded automatically by Coyote with the
 # caller's prompt. So there's no need to set it here.
 # ---------------------------------------------------------------------------
 initial_state:
@@ -123,7 +149,7 @@ start: triage                # ID of the first node to run (must exist in `nodes
 # ---------------------------------------------------------------------------
 # Nodes
 # Each node is keyed by its id. The `id:` inside a node must match its key
-# (it may also be omitted and thus Loki fills it in from the key).
+# (it may also be omitted and thus Coyote fills it in from the key).
 #
 # Node types: agent | script | approval | input | llm | rag | map | end
 # ---------------------------------------------------------------------------
@@ -143,6 +169,19 @@ nodes:
       {{initial_prompt}}
     tools: []                  # Tool whitelist. Omitted or [] = no tools at all.
                                # A list narrows to exactly those entries.
+    # --- Skills on llm nodes (optional) ------------------------------------
+    # `enabled_skills` narrows what this node's model can see / load via the
+    # built-in `skill__list` / `skill__load` / `skill__unload` meta-tools.
+    # Must be a subset of the graph-level `enabled_skills` (the validator
+    # catches violations at load time). `skills_enabled: false` would
+    # disable skills entirely for this node (no meta-tools exposed).
+    # Nothing is auto-loaded: the model decides when to load a skill.
+    skills_enabled: true       # Whether skills are enabled on this llm node; defaults to 'true'
+    enabled_skills:
+      - ai-slop-remover
+    inject_skill_instructions: true   # Override skill-hint injection for just this node. Falls back to
+                                      # agent/graph/global default when omitted.
+    skill_instructions: null          # Per-node skill-hint text override; uses the built-in default when omitted.
     output_schema:             # Optional JSON Schema. The output is parsed to JSON
       type: object             # and its top-level object keys auto-merge into state
       properties:              # (so `topic` / `needs_deep_dive` become {{topic}} etc).
@@ -202,7 +241,7 @@ nodes:
     instructions: "You are a web researcher. Cite every claim."
     prompt: "Web research: {{topic}}. Return findings and sources."
     tools:
-      - web_search_loki
+      - web_search_coyote
       - mcp:ddg-search
     output_schema:
       type: object
@@ -226,13 +265,13 @@ nodes:
   # The script also receives these env vars (parity with bash tools called
   # from normal agents):
   #   GRAPH_STATE / GRAPH_STATE_FILE  state payload (one of the two is set)
-  #   LLM_ROOT_DIR                    loki config dir
+  #   LLM_ROOT_DIR                    coyote config dir
   #   LLM_PROMPT_UTILS_FILE           path to .shared/prompt-utils.sh
   #   LLM_AGENT_DATA_DIR              this agent's data directory
   #   LLM_AGENT_VAR_<NAME>            one per declared `variables:` entry
-  #   PATH                            with loki's functions bin dir prepended
+  #   PATH                            with coyote's functions bin dir prepended
   #   CLICOLOR_FORCE / FORCE_COLOR    so child tools emit ANSI colors
-  # The script's working directory is loki's invocation CWD (not the agent
+  # The script's working directory is coyote's invocation CWD (not the agent
   # directory), matching the behavior of bash tools.
   #
   # This node fires once: after both `retrieve` and `web_search` finish.
@@ -256,13 +295,13 @@ nodes:
     # targets.
 
   # --- agent node ---------------------------------------------------------
-  # Spawns a full Loki sub-agent and waits for it. The child uses its own
+  # Spawns a full Coyote sub-agent and waits for it. The child uses its own
   # tool stack. Agent nodes have no `tools:` field. No schema hint is
   # injected even when `output_schema` is set (unlike llm nodes).
   deep_dive:
     id: deep_dive
     type: agent
-    agent: deep-research       # Name of an existing Loki agent to spawn
+    agent: deep-research       # Name of an existing Coyote agent to spawn
     prompt: |                  # User message sent to the child (templated)
       Research {{topic}} in depth. Existing context:
       {{context}}
@@ -325,7 +364,7 @@ nodes:
     instructions: "Research one subject deeply for a {{audience}} audience."
     prompt: "Research {{subject}}: pull the key facts and one citation."
     tools:
-      - web_search_loki
+      - web_search_coyote
     # No `next:`, `state_updates:`, or `output_schema:` here. Map branches
     # have a strict contract (see `subjects_map.branch` comment).
 
@@ -348,7 +387,7 @@ nodes:
     instructions: "You write concise research summaries for a {{audience}} audience."
     prompt: "Summarize the topic {{topic}}, using your tools as needed."
     tools:                     # Narrow whitelist: exactly these entries, nothing else
-      - web_search_loki        #   an exact global-tool / custom-tool name
+      - web_search_coyote        #   an exact global-tool / custom-tool name
       - mcp:ddg-search         #   `mcp:<server>` includes that server's functions
     model: claude:claude-haiku-4-5  # Optional per-node model override
     temperature: 0.3           # Optional per-node sampling override