feat: Created the --auth-mcp CLI flag to let users auth with remote MCP servers without needing to be in the REPL

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
-      description: Include the Loki log file to help diagnose the issue. (`loki --info` to see the log_path)
+      label: Coyote log
+      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`                      |
-        | Mac     | `~/Library/Logs/loki/loki.log`                |
-        | Windows | `C:\Users\<User>\AppData\Local\loki\loki.log` |
+        | Linux   | `~/.cache/coyote/coyote.log`                      |
+        | Mac     | `~/Library/Logs/coyote/coyote.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**
-      placeholder: "loki 0.1.0"
+        **Make sure that you are using the [latest coyote release](https://github.com/Dark-Alex-17/coyote/releases) or a newer main build**
+      placeholder: "coyote 0.1.0"
     validations:
       required: true

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

@@ -0,0 +1,11 @@
+### AI assistance (if any):
+- List tools here and files touched by them
+
+### Authorship & Understanding
+
+- [ ] I wrote or heavily modified this code myself
+- [ ] I understand how it works end-to-end
+- [ ] I can maintain this code in the future
+- [ ] No undisclosed AI-generated code was used
+- [ ] If AI assistance was used, it is documented below
+

.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
-          rm homebrew-loki/Formula/loki.rb
-          cp loki.rb homebrew-loki/Formula
-          cd homebrew-loki
+          git clone https://Dark-Alex-17:${{ secrets.COYOTE_GITHUB_TOKEN }}@github.com/Dark-Alex-17/homebrew-coyote.git
+          rm homebrew-coyote/Formula/coyote.rb
+          cp coyote.rb homebrew-coyote/Formula
+          cd homebrew-coyote
           git add .
-          git diff-index --quiet HEAD || git commit -am "Update formula for Loki release ${{ env.RELEASE_VERSION }}"
-          git push https://$TOKEN@github.com/Dark-Alex-17/homebrew-loki.git
+          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-coyote.git
 
   publish-crate:
     needs: publish-github-release

.gitignore

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

CHANGELOG.md

@@ -1,10 +1,352 @@
+## 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
+
+- Added `todo__clear` function to the todo system and updated REPL commands to have a .clear todo as well for significant changes in agent direction
+- Added available tools to prompts for sisyphus and code-reviewer agent families
+- Added available tools to coder prompt
+- Improved token efficiency when delegating from sisyphus -> coder
+- modified sisyphus agents to use the new ddg-search MCP server for web searches instead of built-in model searches
+- Added support for specifying a custom response to multiple-choice prompts when nothing suits the user's needs
+- Supported theming in the inquire prompts in the REPL
+- Added the duckduckgo-search MCP server for searching the web (in addition to the built-in tools for web searches)
+- Support for Gemini OAuth
+- Support authenticating or refreshing OAuth for supported clients from within the REPL
+- Allow first-runs to select OAuth for supported providers
+- Support OAuth authentication flows for Claude
+- Improved MCP server spinup and spindown when switching contexts or settings in the REPL: Modify existing config rather than stopping all servers always and re-initializing if unnecessary
+- Allow the explore agent to run search queries for understanding docs or API specs
+- Allow the oracle to perform web searches for deeper research
+- Added web search support to the main sisyphus agent to answer user queries
+- 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 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
+- Full passive task queue integration for parallelization of subagents
+- Implemented initial scaffolding for built-in sub-agent spawning tool call operations
+- Initial models for agent parallelization
+- Added interactive prompting between the LLM and the user in Sisyphus using the built-in Bash utils scripts
+
+### Fix
+
+- Clarified user text input interaction
+- recursion bug with similarly named Bash search functions in the explore agent
+- updated the error for unauthenticated oauth to include the REPL .authenticated command
+- Corrected a bug in the coder agent that wasn't outputting a summary of the changes made, so the parent Sisyphus agent has no idea if the agent worked or not
+- Claude code system prompt injected into claude requests to make them valid once again
+- Do not inject tools when models don't support them; detect this conflict before API calls happen
+- The REPL .authenticate command works from within sessions, agents, and roles with pre-configured models
+- Implemented the path normalization fix for the oracle and explore agents
+- Updated the atlassian MCP server endpoint to account for future deprecation
+- Fixed a bug in the coder agent that was causing the agent to create absolute paths from the current directory
+- the updated regex for secrets injection broke MCP server secrets interpolation because the regex greedily matched on new lines, replacing too much content. This fix just ignores commented out lines in YAML files by skipping commented out lines.
+- Don't try to inject secrets into commented-out lines in the config
+- Removed top_p parameter from some agents so they can work across model providers
+- Improved sub-agent stdout and stderr output for users to follow
+- Inject agent variables into environment variables for global tool calls when invoked from agents to modify global tool behavior
+- Removed the unnecessary execute_commands tool from the oracle agent
+- Added auto_confirm to the coder agent so sub-agent spawning doesn't freeze
+- Fixed a bug in the new supervisor and todo built-ins that was causing errors with OpenAI models
+- Added condition to sisyphus to always output a summary to clearly indicate completion
+- Updated the sisyphus prompt to explicitly tell it to delegate to the coder agent when it wants to write any code at all except for trivial changes
+- Added back in the auto_confirm variable into sisyphus
+- Removed the now unnecessary is_stale_response that was breaking auto-continuing with parallel agents
+- Bypassed enabled_tools for user interaction tools so if function calling is enabled at all, the LLM has access to the user interaction tools when in REPL mode
+- When parallel agents run, only write to stdout from the parent and only display the parent's throbber
+- Forgot to implement support for failing a task and keep all dependents blocked
+- Clean up orphaned sub-agents when the parent agent
+- Fixed the bash prompt utils so that they correctly show output when being run by a tool invocation
+- Forgot to automatically add the bidirectional communication back up to parent agents from sub-agents (i.e. need to be able to check inbox and send messages)
+- Agent delegation tools were not being passed into the {{__tools__}} placeholder so agents weren't delegating to subagents
+
+### Refactor
+
+- Made the oauth module more generic so it can support loopback OAuth (not just manual)
+- Changed the default session name for Sisyphus to temp (to require users to explicitly name sessions they wish to save)
+- Updated the sisyphus agent to use the built-in user interaction tools instead of custom bash-based tools
+- Cleaned up some left-over implementation stubs
+
 ## v0.2.0 (2026-02-14)
 
 ### Feat
 
 - 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
@@ -64,8 +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
-- Integrated gman with Loki to create a vault and added flags to configure the Loki vault
+- added REPL support for interacting with the Coyote 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:
 
@@ -76,6 +76,13 @@ Then, you can run workflows locally without having to commit and see if the GitH
 act -W .github/workflows/release.yml --input_type bump=minor
 ```
 
+ ## Authorship Policy
+
+All code in this repository is written and reviewed by humans. AI-generated code (e.g., Copilot, ChatGPT,
+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"
-version = "0.2.0"
+name = "coyote-ai"
+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"
-repository = "https://github.com/Dark-Alex-17/loki"
+homepage = "https://github.com/Dark-Alex-17/coyote"
+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]
@@ -18,10 +18,11 @@ anyhow = "1.0.69"
 bytes = "1.4.0"
 clap = { version = "4.5.40", features = ["cargo", "derive", "wrap_help"] }
 dirs = "6.0.0"
+dunce = "1.0.5"
 futures-util = "0.3.29"
-inquire = "0.7.0"
+inquire = "0.9.4"
 is-terminal = "0.4.9"
-reedline = "0.40.0"
+reedline = "0.47.0"
 serde = { version = "1.0.152", features = ["derive"] }
 serde_json = { version = "1.0.93", features = ["preserve_order"] }
 serde_yaml = "0.9.17"
@@ -33,11 +34,7 @@ tokio = { version = "1.34.0", features = [
   "rt-multi-thread",
   "full",
 ] }
-tokio-graceful = "0.2.2"
-tokio-stream = { version = "0.1.15", default-features = false, features = [
-  "sync",
-] }
-crossterm = "0.28.1"
+crossterm = "0.29.0"
 chrono = "0.4.23"
 bincode = { version = "2.0.0", features = [
   "serde",
@@ -50,28 +47,24 @@ nu-ansi-term = "0.50.0"
 async-trait = "0.1.74"
 textwrap = "0.16.0"
 ansi_colours = "1.2.2"
-reqwest-eventsource = "0.6.0"
+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"
 async-recursion = "1.1.1"
 http = "1.1.0"
-http-body-util = "0.1"
-hyper = { version = "1.0", features = ["full"] }
-hyper-util = { version = "0.1", features = ["server-auto", "client-legacy"] }
-time = { version = "0.3.36", features = ["macros"] }
 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"
-unicode-segmentation = "1.11.0"
 json-patch = { version = "4.0.0", default-features = false }
 bitflags = "2.5.0"
 path-absolutize = "3.1.1"
 hnsw_rs = "0.3.0"
-rayon = "1.10.0"
 uuid = { version = "1.9.1", features = ["v4"] }
 scraper = { version = "0.23.1", default-features = false, features = [
   "deterministic",
@@ -88,23 +81,41 @@ duct = "1.0.0"
 argc = "1.23.0"
 strum_macros = "0.27.2"
 indoc = "2.0.6"
-rmcp = { version = "0.6.1", features = ["client", "transport-child-process"] }
+rmcp = { version = "1.5.0", features = [
+  "client",
+  "transport-child-process",
+  "transport-streamable-http-client-reqwest",
+  "reqwest-native-tls",
+] }
 num_cpus = "1.17.0"
-rustpython-parser = "0.4.0"
-rustpython-ast = "0.4.0"
+tree-sitter = "0.26.8"
+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 = "0.3.0"
+gman = "0.5.0"
 clap_complete_nushell = "4.5.9"
+open = "5"
+rand = { version = "0.10.0", features = ["default"] }
+url = "2.5.8"
+self_update = { version = "0.44", default-features = false, features = [
+  "reqwest",
+  "rustls",
+  "archive-tar",
+  "compression-flate2",
+  "archive-zip",
+  "compression-zip-deflate",
+] }
 
 [dependencies.reqwest]
-version = "0.12.0"
+version = "0.13.3"
 features = [
   "json",
   "multipart",
+  "stream",
+  "form",
   "socks",
-  "rustls-tls",
-  "rustls-tls-native-roots",
+  "rustls",
 ]
 default-features = false
 
@@ -114,7 +125,7 @@ default-features = false
 features = ["parsing", "regex-onig", "plist-load"]
 
 [target.'cfg(target_os = "macos")'.dependencies]
-crossterm = { version = "0.28.1", features = ["use-dev-tty"] }
+crossterm = { version = "0.29.0", features = ["use-dev-tty"] }
 
 [target.'cfg(target_os = "linux")'.dependencies]
 arboard = { version = "3.3.0", default-features = false, features = [
@@ -126,10 +137,10 @@ arboard = { version = "3.3.0", default-features = false }
 
 [dev-dependencies]
 pretty_assertions = "1.4.0"
-rand = "0.9.0"
+serial_test = "3"
 
 [[bin]]
-name = "loki"
+name = "coyote"
 path = "src/main.rs"
 
 [profile.release]

README.md

@@ -1,119 +1,116 @@
-# 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)
-![LOC](https://tokei.rs/b1/github/Dark-Alex-17/loki?category=code)
-[![crates.io link](https://img.shields.io/crates/v/loki-ai.svg)](https://crates.io/crates/loki-ai)
-![Release](https://img.shields.io/github/v/release/Dark-Alex-17/loki?color=%23c694ff)
-![Crate.io downloads](https://img.shields.io/crates/d/loki-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)
+![Test](https://github.com/Dark-Alex-17/coyote/actions/workflows/ci.yaml/badge.svg)
+[![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/coyote?color=%23c694ff)
+![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/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 
-in as little time as possible.
+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](https://github.com/Dark-Alex-17/coyote/wiki/Sharing-Configurations) for more information.
 
-![Agent example](./docs/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](./docs/AICHAT-MIGRATION.md) 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](./docs/AICHAT-MIGRATION.md): Coming from AIChat? Follow the migration guide to get started.
-* [Installation](#install): Install Loki
-* [Getting Started](#getting-started): Get started with Loki by doing first-run setup steps.
-* [REPL](./docs/REPL.md): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Loki.
-  * [Custom REPL Prompt](./docs/REPL-PROMPT.md): Customize the REPL prompt to provide useful contextual information.
-* [Vault](./docs/VAULT.md): Securely store and manage sensitive information such as API keys and credentials.
-* [Shell Integrations](./docs/SHELL-INTEGRATIONS.md): Seamlessly integrate Loki with your shell environment for enhanced command-line assistance.
-* [Function Calling](./docs/function-calling/TOOLS.md#Tools): Leverage function calling capabilities to extend Loki's functionality with custom tools
-    * [Creating Custom Tools](./docs/function-calling/CUSTOM-TOOLS.md): You can create your own custom tools to enhance Loki's capabilities.
-        * [Create Custom Python Tools](./docs/function-calling/CUSTOM-TOOLS.md#custom-python-based-tools)
-        * [Create Custom Bash Tools](./docs/function-calling/CUSTOM-BASH-TOOLS.md)
-            * [Bash Prompt Utilities](./docs/function-calling/BASH-PROMPT-HELPERS.md)
-* [First-Class MCP Server Support](./docs/function-calling/MCP-SERVERS.md): Easily connect and interact with MCP servers for advanced functionality.
-* [Macros](./docs/MACROS.md): Automate repetitive tasks and workflows with Loki "scripts" (macros).
-* [RAG](./docs/RAG.md): Retrieval-Augmented Generation for enhanced information retrieval and generation.
-* [Sessions](/docs/SESSIONS.md): Manage and persist conversational contexts and settings across multiple interactions.
-* [Roles](./docs/ROLES.md): Customize model behavior for specific tasks or domains.
-* [Agents](/docs/AGENTS.md): Leverage AI agents to perform complex tasks and workflows.
-    * [Todo System](./docs/TODO-SYSTEM.md): Built-in task tracking for improved agent reliability with smaller models.
-* [Environment Variables](./docs/ENVIRONMENT-VARIABLES.md): Override and customize your Loki configuration at runtime with environment variables.
-* [Client Configurations](./docs/clients/CLIENTS.md): Configuration instructions for various LLM providers.
-    * [Patching API Requests](./docs/clients/PATCHES.md): Learn how to patch API requests for advanced customization.
-* [Custom Themes](./docs/THEMES.md): Change the look and feel of Loki to your preferences with custom themes.
-* [History](#history): A history of how Loki came to be.
+* [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 Coyote
+* [Getting Started](#getting-started): Get started with Coyote by doing first-run setup steps.
+* [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/coyote/wiki/REPL): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Coyote.
+  * [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/coyote/wiki/Vault): Securely store and manage sensitive information such as API keys and credentials.
+* [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.
+* [Shell Integrations](https://github.com/Dark-Alex-17/coyote/wiki/Shell-Integrations): Seamlessly integrate Coyote with your shell environment for enhanced command-line assistance.
+* [Function Calling](https://github.com/Dark-Alex-17/coyote/wiki/Tools): Leverage function calling capabilities to extend Coyote's functionality with custom 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 Python Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-python-based-tools)
+        * [Create Custom TypeScript Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Tools#custom-typescript-based-tools)
+        * [Create Custom Bash Tools](https://github.com/Dark-Alex-17/coyote/wiki/Custom-Bash-Tools)
+            * [Bash Prompt Utilities](https://github.com/Dark-Alex-17/coyote/wiki/Bash-Prompt-Helpers)
+* [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.
+* [Macros](https://github.com/Dark-Alex-17/coyote/wiki/Macros): Automate repetitive tasks and workflows with Coyote "scripts" (macros).
+* [RAG](https://github.com/Dark-Alex-17/coyote/wiki/RAG): Retrieval-Augmented Generation for enhanced information retrieval and generation.
+* [Sessions](https://github.com/Dark-Alex-17/coyote/wiki/Sessions): Manage and persist conversational contexts and settings across multiple interactions.
+* [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]`.
+* [Roles](https://github.com/Dark-Alex-17/coyote/wiki/Roles): Customize model behavior for specific tasks or domains.
+* [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.
+* [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.
+    * [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).
+* [Todo System](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System): Built-in task tracking for improved LLM reliability with smaller models.
+* [Environment Variables](https://github.com/Dark-Alex-17/coyote/wiki/Environment-Variables): Override and customize your Coyote configuration at runtime with environment variables.
+* [Client Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Clients): Configuration instructions for various LLM providers.
+    * [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`
-* [jira (optional)](https://github.com/ankitpokhrel/jira-cli/wiki/Installation) (For the `query_jira_issues` tool)
-    * `brew tap ankitpokhrel/jira-cli && brew install jira-cli`
-    * You'll need to [create a JIRA API token](https://id.atlassian.com/manage-profile/security/api-tokens) for authentication
-    * Then, save it as an environment variable to your shell profile:
-      ```sh
-      # ~/.bashrc or ~/.zshrc
-      export JIRA_API_TOKEN="your_jira_api_token_here"
-      ```
-    * Then run `jira init`, select installation type as `cloud`, and provide the required details to generate a config
-      file for the Jira CLI.
 * [usql](https://github.com/xo/usql) (For the `sql` agent)
     * `brew install xo/xo/usql`
 * [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`
 
-These tools are used to provide various functionalities within Loki, such as document processing, JSON manipulation,
-interaction with Jira, and they are used within agents and tools.
+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 install loki
+brew tap Dark-Alex-17/coyote
+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) |
 |----------------|-----------------|
@@ -124,60 +121,103 @@ 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`)
-4. Now you can run `loki`!
+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 `coyote`!
+
+## Updating
+Coyote can update itself in place to the latest GitHub release. Run `coyote --update`
+for the newest release, or `coyote --update v0.4.0` for a specific version:
+
+```shell
+coyote --update
+coyote --update v0.4.0
+```
+
+The same is available from within the REPL via `.update` and `.update v0.4.0`.
+
+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 coyote` for Homebrew,
+or `cargo install --locked coyote-ai` for Cargo.
+
+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
+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/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
+coyote --authenticate my-claude-oauth
+# Or via the REPL: .authenticate
+```
+
+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
-corresponding [shell integration script](./scripts/shell-integration) to your shell. Then, you can invoke Loki to convert natural language to 
+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 Coyote to convert natural language to 
 shell commands by pressing `Alt-e`. For example:
 
 ```shell
@@ -187,18 +227,18 @@ 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                                                                                                                                             |
@@ -208,34 +248,34 @@ 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](./docs/REPL.md) 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>  |
+| `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 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                                                                                                      |
@@ -247,7 +287,7 @@ 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

@@ -2,81 +2,19 @@
 # Shared Agent Utilities - Minimal, focused helper functions
 set -euo pipefail
 
-#############################
-## CONTEXT FILE MANAGEMENT ##
-#############################
-
-get_context_file() {
-  local project_dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
-  echo "${project_dir}/.loki-context"
-}
-
-# Initialize context file for a new task
-# Usage: init_context "Task description"
-init_context() {
-  local task="$1"
-  local project_dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
-  local context_file
-  context_file=$(get_context_file)
-  
-  cat > "${context_file}" <<EOF
-## Project: ${project_dir}
-## Task: ${task}
-## Started: $(date -Iseconds)
-
-### Prior Findings
-
-EOF
-}
-
-# Append findings to the context file
-# Usage: append_context "agent_name" "finding summary
-append_context() {
-  local agent="$1"
-  local finding="$2"
-  local context_file
-  context_file=$(get_context_file)
-
-  if [[ -f "${context_file}" ]]; then
-    {
-      echo ""
-      echo "[${agent}]:"
-      echo "${finding}"
-    } >> "${context_file}"
-  fi
-}
-
-# Read the current context (returns empty string if no context)
-# Usage: context=$(read_context)
-read_context() {
-  local context_file
-  context_file=$(get_context_file)
-  
-  if [[ -f "${context_file}" ]]; then
-    cat "${context_file}"
-  fi
-}
-
-# Clear the context file
-clear_context() {
-  local context_file
-  context_file=$(get_context_file)
-  rm -f "${context_file}"
-}
-
 #######################
 ## PROJECT DETECTION ##
 #######################
 
 # 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
@@ -94,7 +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
 }
@@ -279,9 +217,9 @@ _detect_with_llm() {
   evidence=$(_gather_project_evidence "${dir}")
   local prompt
   prompt=$(cat <<-EOF
-		
+
 		Analyze this project directory and determine the project type, primary language, and the correct shell commands to build, test, and check (lint/typecheck) it.
-		
+
 		EOF
 	)
   prompt+=$'\n'"${evidence}"$'\n'
@@ -300,7 +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)
@@ -348,77 +286,11 @@ detect_project() {
   echo '{"type":"unknown","build":"","test":"","check":""}'
 }
 
-######################
-## AGENT INVOCATION ##
-######################
-
-# Invoke a subagent with optional context injection
-# Usage: invoke_agent <agent_name> <prompt> [extra_args...]
-invoke_agent() {
-  local agent="$1"
-  local prompt="$2"
-  shift 2
-
-  local context
-  context=$(read_context)
-
-  local full_prompt
-  if [[ -n "${context}" ]]; then
-    full_prompt="## Orchestrator Context
-
-The orchestrator (sisyphus) has gathered this context from prior work:
-
-<context>
-${context}
-</context>
-
-## Your Task
-
-${prompt}"
-  else
-    full_prompt="${prompt}"
-  fi
-
-  env AUTO_CONFIRM=true loki --agent "${agent}" "$@" "${full_prompt}" 2>&1
-}
-
-# Invoke a subagent and capture a summary of its findings
-# Usage: result=$(invoke_agent_with_summary "explore" "find auth patterns")
-invoke_agent_with_summary() {
-  local agent="$1"
-  local prompt="$2"
-  shift 2
-
-  local output
-  output=$(invoke_agent "${agent}" "${prompt}" "$@")
-
-  local summary=""
-
-  if echo "${output}" | grep -q "FINDINGS:"; then
-    summary=$(echo "${output}" | sed -n '/FINDINGS:/,/^[A-Z_]*COMPLETE/p' | grep "^- " | sed 's/^- /  - /')
-  elif echo "${output}" | grep -q "CODER_COMPLETE:"; then
-    summary=$(echo "${output}" | grep "CODER_COMPLETE:" | sed 's/CODER_COMPLETE: *//')
-  elif echo "${output}" | grep -q "ORACLE_COMPLETE"; then
-    summary=$(echo "${output}" | sed -n '/^## Recommendation/,/^## /{/^## Recommendation/d;/^## /d;p}' | sed '/^$/d' | head -10)
-  fi
-
-  # Failsafe: extract up to 5 meaningful lines if no markers found
-  if [[ -z "${summary}" ]]; then
-    summary=$(echo "${output}" | grep -v "^$" | grep -v "^#" | grep -v "^\-\-\-" | tail -10 | head -5)
-  fi
-
-  if [[ -n "${summary}" ]]; then
-    append_context "${agent}" "${summary}"
-  fi
-
-  echo "${output}"
-}
-
 ###########################
 ## FILE SEARCH UTILITIES ##
 ###########################
 
-search_files() {
+_search_files() {
   local pattern="$1"
   local dir="${2:-.}"
   

assets/agents/code-reviewer/README.md

@@ -0,0 +1,36 @@
+# Code Reviewer
+
+A CodeRabbit-style code review orchestrator that coordinates per-file reviews and synthesizes findings into a unified 
+report.
+
+This agent acts as the manager for the review process, delegating actual file analysis to **[File Reviewer](../file-reviewer/README.md)** 
+agents while handling coordination and final reporting.
+
+## Features
+
+- 🤖 **Orchestration**: Spawns parallel reviewers for each changed file.
+- 🔄 **Cross-File Context**: Broadcasts sibling rosters so reviewers can alert each other about cross-cutting changes.
+- 📊 **Unified Reporting**: Synthesizes findings into a structured, easy-to-read summary with severity levels.
+- ⚡ **Parallel Execution**: Runs reviews concurrently for maximum speed.
+
+## 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
+them), and modify the agent definition to look like this:
+
+```yaml
+# ...
+
+mcp_servers:
+  - jetbrains # The name of your configured IDE MCP server
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+#  - execute_command.sh
+
+# ...
+```
+

assets/agents/code-reviewer/config.yaml

@@ -0,0 +1,163 @@
+name: code-reviewer
+description: CodeRabbit-style code reviewer - spawns per-file reviewers, synthesizes findings
+version: 2.0.0
+
+auto_continue: true
+max_auto_continues: 20
+inject_todo_instructions: true
+
+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
+    default: '.'
+
+global_tools:
+  - fs_read.sh
+  - fs_cat.sh
+  - fs_grep.sh
+  - fs_glob.sh
+  - execute_command.sh
+
+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. 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:** 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
+
+  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.
+
+  ```
+  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>
+  "
+  ```
+
+  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:
+
+  ```
+  agent__send_message --to <agent_id> --message "SIBLING_ROSTER:
+  - <agent_id_1>: reviewing <file_1>
+  - <agent_id_2>: reviewing <file_2>
+  ...
+  Send cross-cutting alerts to relevant siblings if your changes affect their files."
+  ```
+
+  ## Diff Parsing
+
+  Split the diff by file. Each file's diff starts with `diff --git a/<path> b/<path>`. Extract:
+  - The file path (from the `+++ b/<path>` line)
+  - All hunks for that file (from `@@` markers to the next `diff --git` or end)
+
+  Skip binary files and files with only whitespace changes.
+
+  ## Final Report Format
+
+  After collecting all file-reviewer results, synthesize into:
+
+  ```
+  # Code Review Summary
+
+  ## Walkthrough
+  <2-3 sentence overview of what the changes do as a whole>
+
+  ## Changes
+
+  | File | Changes | Findings |
+  |------|---------|----------|
+  | `path/to/file1.rs` | <brief description> | 🔴 1 🟡 2 🟢 1 |
+  | `path/to/file2.rs` | <brief description> | 🟢 2 💡 1 |
+
+  ## Detailed Findings
+
+  ### `path/to/file1.rs`
+  <paste file-reviewer's findings here, cleaned up>
+
+  ### `path/to/file2.rs`
+  <paste file-reviewer's findings here, cleaned up>
+
+  ## Cross-File Concerns
+  <any cross-cutting issues identified by the teammate pattern>
+
+  ---
+  *Reviewed N files, found X critical, Y warnings, Z suggestions, W nitpicks*
+  ```
+
+  ## Edge Cases
+
+  - **Single file changed:** Still spawn one file-reviewer (for consistency), skip roster broadcast
+  - **Too many files (>10):** Group small files (< 20 lines changed) and review them together
+  - **No changes found:** Report "No changes to review" and exit
+  - **Binary files:** Skip with a note in the summary
+
+  ## Rules
+
+  1. **Always use `get_diff` first:** Don't assume what changed
+  2. **Spawn in parallel:** All file-reviewers should be spawned before collecting any
+  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}}
+  - CWD: {{__cwd__}}
+  - Shell: {{__shell__}}
+  
+  ## Available Tools:
+  {{__tools__}}

assets/agents/code-reviewer/tools.sh

@@ -0,0 +1,478 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+# shellcheck disable=SC1090
+source "$LLM_PROMPT_UTILS_FILE"
+source "$LLM_ROOT_DIR/agents/.shared/utils.sh"
+
+# @env LLM_OUTPUT=/dev/stdout
+# @env LLM_AGENT_VAR_PROJECT_DIR=.
+# @describe Code review orchestrator tools
+
+_project_dir() {
+  local dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
+  (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
+}
+
+# @cmd Get git diff for code review. Returns staged changes, or unstaged if nothing is staged, or HEAD~1 diff if working tree is clean.
+# @option --base Optional base ref to diff against (e.g., "main", "HEAD~3", a commit SHA)
+get_diff() {
+  local project_dir
+  project_dir=$(_project_dir)
+  # shellcheck disable=SC2154
+  local base="${argc_base:-}"
+
+  local diff_output=""
+
+  if [[ -n "${base}" ]]; then
+    diff_output=$(cd "${project_dir}" && git diff "${base}" 2>&1) || true
+  else
+    diff_output=$(cd "${project_dir}" && git diff --cached 2>&1) || true
+
+    if [[ -z "${diff_output}" ]]; then
+      diff_output=$(cd "${project_dir}" && git diff 2>&1) || true
+    fi
+
+    if [[ -z "${diff_output}" ]]; then
+      diff_output=$(cd "${project_dir}" && git diff HEAD~1 2>&1) || true
+    fi
+  fi
+
+  if [[ -z "${diff_output}" ]]; then
+    warn "No changes found to review" >> "$LLM_OUTPUT"
+    return 0
+  fi
+
+  local file_count
+  file_count=$(echo "${diff_output}" | grep -c '^diff --git' || true)
+
+  {
+    info "Diff contains changes to ${file_count} file(s)"
+    echo ""
+    echo "${diff_output}"
+  } >> "$LLM_OUTPUT"
+}
+
+# @cmd Get list of changed files with stats
+# @option --base Optional base ref to diff against
+get_changed_files() {
+  local project_dir
+  project_dir=$(_project_dir)
+  local base="${argc_base:-}"
+
+  local stat_output=""
+
+  if [[ -n "${base}" ]]; then
+    stat_output=$(cd "${project_dir}" && git diff --stat "${base}" 2>&1) || true
+  else
+    stat_output=$(cd "${project_dir}" && git diff --cached --stat 2>&1) || true
+
+    if [[ -z "${stat_output}" ]]; then
+      stat_output=$(cd "${project_dir}" && git diff --stat 2>&1) || true
+    fi
+
+    if [[ -z "${stat_output}" ]]; then
+      stat_output=$(cd "${project_dir}" && git diff --stat HEAD~1 2>&1) || true
+    fi
+  fi
+
+  if [[ -z "${stat_output}" ]]; then
+    warn "No changes found" >> "$LLM_OUTPUT"
+    return 0
+  fi
+
+  {
+    info "Changed files:"
+    echo ""
+    echo "${stat_output}"
+  } >> "$LLM_OUTPUT"
+}
+
+# @cmd Get project structure and type information
+get_project_info() {
+  local project_dir
+  project_dir=$(_project_dir)
+
+  local project_info
+  project_info=$(detect_project "${project_dir}")
+
+  {
+    info "Project: ${project_dir}"
+    echo "Type: $(echo "${project_info}" | jq -r '.type')"
+    echo ""
+    get_tree "${project_dir}" 2
+  } >> "$LLM_OUTPUT"
+}
+
+# ARGC-BUILD {
+# This block was generated by argc (https://github.com/sigoden/argc).
+# Modifying it manually is not recommended
+
+_argc_run() {
+    if [[ "${1:-}" == "___internal___" ]]; then
+        _argc_die "error: unsupported ___internal___ command"
+    fi
+    if [[ "${OS:-}" == "Windows_NT" ]] && [[ -n "${MSYSTEM:-}" ]]; then
+        set -o igncr
+    fi
+    argc__args=("$(basename "$0" .sh)" "$@")
+    argc__positionals=()
+    _argc_index=1
+    _argc_len="${#argc__args[@]}"
+    _argc_tools=()
+    _argc_parse
+    if [ -n "${argc__fn:-}" ]; then
+        $argc__fn "${argc__positionals[@]}"
+    fi
+}
+
+_argc_usage() {
+    cat <<-'EOF'
+Code review orchestrator tools
+
+USAGE:  <COMMAND>
+
+COMMANDS:
+  get_diff           Get git diff for code review. Returns staged changes, or unstaged if nothing is staged, or HEAD~1 diff if working tree is clean. [aliases: get-diff]
+  get_changed_files  Get list of changed files with stats [aliases: get-changed-files]
+  get_project_info   Get project structure and type information [aliases: get-project-info]
+
+ENVIRONMENTS:
+  LLM_OUTPUT                 [default: /dev/stdout]
+  LLM_AGENT_VAR_PROJECT_DIR  [default: .]
+EOF
+    exit
+}
+
+_argc_version() {
+    echo  0.0.0
+    exit
+}
+
+_argc_parse() {
+    local _argc_key _argc_action
+    local _argc_subcmds="get_diff, get-diff, get_changed_files, get-changed-files, get_project_info, get-project-info"
+    while [[ $_argc_index -lt $_argc_len ]]; do
+        _argc_item="${argc__args[_argc_index]}"
+        _argc_key="${_argc_item%%=*}"
+        case "$_argc_key" in
+        --help | -help | -h)
+            _argc_usage
+            ;;
+        --version | -version | -V)
+            _argc_version
+            ;;
+        --)
+            _argc_dash="${#argc__positionals[@]}"
+            argc__positionals+=("${argc__args[@]:$((_argc_index + 1))}")
+            _argc_index=$_argc_len
+            break
+            ;;
+        get_diff | get-diff)
+            _argc_index=$((_argc_index + 1))
+            _argc_action=_argc_parse_get_diff
+            break
+            ;;
+        get_changed_files | get-changed-files)
+            _argc_index=$((_argc_index + 1))
+            _argc_action=_argc_parse_get_changed_files
+            break
+            ;;
+        get_project_info | get-project-info)
+            _argc_index=$((_argc_index + 1))
+            _argc_action=_argc_parse_get_project_info
+            break
+            ;;
+        help)
+            local help_arg="${argc__args[$((_argc_index + 1))]:-}"
+            case "$help_arg" in
+            get_diff | get-diff)
+                _argc_usage_get_diff
+                ;;
+            get_changed_files | get-changed-files)
+                _argc_usage_get_changed_files
+                ;;
+            get_project_info | get-project-info)
+                _argc_usage_get_project_info
+                ;;
+            "")
+                _argc_usage
+                ;;
+            *)
+                _argc_die "error: invalid value \`$help_arg\` for \`<command>\`"$'\n'"  [possible values: $_argc_subcmds]"
+                ;;
+            esac
+            ;;
+        *)
+            _argc_die "error: \`\` requires a subcommand but one was not provided"$'\n'"  [subcommands: $_argc_subcmds]"
+            ;;
+        esac
+    done
+    if [[ -n "${_argc_action:-}" ]]; then
+        $_argc_action
+    else
+        _argc_usage
+    fi
+}
+
+_argc_usage_get_diff() {
+    cat <<-'EOF'
+Get git diff for code review. Returns staged changes, or unstaged if nothing is staged, or HEAD~1 diff if working tree is clean.
+
+USAGE:  get_diff [OPTIONS]
+
+OPTIONS:
+      --base <BASE>  Optional base ref to diff against (e.g., "main", "HEAD~3", a commit SHA)
+  -h, --help         Print help
+
+ENVIRONMENTS:
+  LLM_OUTPUT                 [default: /dev/stdout]
+  LLM_AGENT_VAR_PROJECT_DIR  [default: .]
+EOF
+    exit
+}
+
+_argc_parse_get_diff() {
+    local _argc_key _argc_action
+    local _argc_subcmds=""
+    while [[ $_argc_index -lt $_argc_len ]]; do
+        _argc_item="${argc__args[_argc_index]}"
+        _argc_key="${_argc_item%%=*}"
+        case "$_argc_key" in
+        --help | -help | -h)
+            _argc_usage_get_diff
+            ;;
+        --)
+            _argc_dash="${#argc__positionals[@]}"
+            argc__positionals+=("${argc__args[@]:$((_argc_index + 1))}")
+            _argc_index=$_argc_len
+            break
+            ;;
+        --base)
+            _argc_take_args "--base <BASE>" 1 1 "-" ""
+            _argc_index=$((_argc_index + _argc_take_args_len + 1))
+            if [[ -z "${argc_base:-}" ]]; then
+                argc_base="${_argc_take_args_values[0]:-}"
+            else
+                _argc_die "error: the argument \`--base\` cannot be used multiple times"
+            fi
+            ;;
+        *)
+            if _argc_maybe_flag_option "-" "$_argc_item"; then
+                _argc_die "error: unexpected argument \`$_argc_key\` found"
+            fi
+            argc__positionals+=("$_argc_item")
+            _argc_index=$((_argc_index + 1))
+            ;;
+        esac
+    done
+    if [[ -n "${_argc_action:-}" ]]; then
+        $_argc_action
+    else
+        argc__fn=get_diff
+        if [[ "${argc__positionals[0]:-}" == "help" ]] && [[ "${#argc__positionals[@]}" -eq 1 ]]; then
+            _argc_usage_get_diff
+        fi
+        if [[ -z "${LLM_OUTPUT:-}" ]]; then
+            export LLM_OUTPUT=/dev/stdout
+        fi
+        if [[ -z "${LLM_AGENT_VAR_PROJECT_DIR:-}" ]]; then
+            export LLM_AGENT_VAR_PROJECT_DIR=.
+        fi
+    fi
+}
+
+_argc_usage_get_changed_files() {
+    cat <<-'EOF'
+Get list of changed files with stats
+
+USAGE:  get_changed_files [OPTIONS]
+
+OPTIONS:
+      --base <BASE>  Optional base ref to diff against
+  -h, --help         Print help
+
+ENVIRONMENTS:
+  LLM_OUTPUT                 [default: /dev/stdout]
+  LLM_AGENT_VAR_PROJECT_DIR  [default: .]
+EOF
+    exit
+}
+
+_argc_parse_get_changed_files() {
+    local _argc_key _argc_action
+    local _argc_subcmds=""
+    while [[ $_argc_index -lt $_argc_len ]]; do
+        _argc_item="${argc__args[_argc_index]}"
+        _argc_key="${_argc_item%%=*}"
+        case "$_argc_key" in
+        --help | -help | -h)
+            _argc_usage_get_changed_files
+            ;;
+        --)
+            _argc_dash="${#argc__positionals[@]}"
+            argc__positionals+=("${argc__args[@]:$((_argc_index + 1))}")
+            _argc_index=$_argc_len
+            break
+            ;;
+        --base)
+            _argc_take_args "--base <BASE>" 1 1 "-" ""
+            _argc_index=$((_argc_index + _argc_take_args_len + 1))
+            if [[ -z "${argc_base:-}" ]]; then
+                argc_base="${_argc_take_args_values[0]:-}"
+            else
+                _argc_die "error: the argument \`--base\` cannot be used multiple times"
+            fi
+            ;;
+        *)
+            if _argc_maybe_flag_option "-" "$_argc_item"; then
+                _argc_die "error: unexpected argument \`$_argc_key\` found"
+            fi
+            argc__positionals+=("$_argc_item")
+            _argc_index=$((_argc_index + 1))
+            ;;
+        esac
+    done
+    if [[ -n "${_argc_action:-}" ]]; then
+        $_argc_action
+    else
+        argc__fn=get_changed_files
+        if [[ "${argc__positionals[0]:-}" == "help" ]] && [[ "${#argc__positionals[@]}" -eq 1 ]]; then
+            _argc_usage_get_changed_files
+        fi
+        if [[ -z "${LLM_OUTPUT:-}" ]]; then
+            export LLM_OUTPUT=/dev/stdout
+        fi
+        if [[ -z "${LLM_AGENT_VAR_PROJECT_DIR:-}" ]]; then
+            export LLM_AGENT_VAR_PROJECT_DIR=.
+        fi
+    fi
+}
+
+_argc_usage_get_project_info() {
+    cat <<-'EOF'
+Get project structure and type information
+
+USAGE:  get_project_info
+
+ENVIRONMENTS:
+  LLM_OUTPUT                 [default: /dev/stdout]
+  LLM_AGENT_VAR_PROJECT_DIR  [default: .]
+EOF
+    exit
+}
+
+_argc_parse_get_project_info() {
+    local _argc_key _argc_action
+    local _argc_subcmds=""
+    while [[ $_argc_index -lt $_argc_len ]]; do
+        _argc_item="${argc__args[_argc_index]}"
+        _argc_key="${_argc_item%%=*}"
+        case "$_argc_key" in
+        --help | -help | -h)
+            _argc_usage_get_project_info
+            ;;
+        --)
+            _argc_dash="${#argc__positionals[@]}"
+            argc__positionals+=("${argc__args[@]:$((_argc_index + 1))}")
+            _argc_index=$_argc_len
+            break
+            ;;
+        *)
+            argc__positionals+=("$_argc_item")
+            _argc_index=$((_argc_index + 1))
+            ;;
+        esac
+    done
+    if [[ -n "${_argc_action:-}" ]]; then
+        $_argc_action
+    else
+        argc__fn=get_project_info
+        if [[ "${argc__positionals[0]:-}" == "help" ]] && [[ "${#argc__positionals[@]}" -eq 1 ]]; then
+            _argc_usage_get_project_info
+        fi
+        if [[ -z "${LLM_OUTPUT:-}" ]]; then
+            export LLM_OUTPUT=/dev/stdout
+        fi
+        if [[ -z "${LLM_AGENT_VAR_PROJECT_DIR:-}" ]]; then
+            export LLM_AGENT_VAR_PROJECT_DIR=.
+        fi
+    fi
+}
+
+_argc_take_args() {
+    _argc_take_args_values=()
+    _argc_take_args_len=0
+    local param="$1" min="$2" max="$3" signs="$4" delimiter="$5"
+    if [[ "$min" -eq 0 ]] && [[ "$max" -eq 0 ]]; then
+        return
+    fi
+    local _argc_take_index=$((_argc_index + 1)) _argc_take_value
+    if [[ "$_argc_item" == *=* ]]; then
+        _argc_take_args_values=("${_argc_item##*=}")
+    else
+        while [[ $_argc_take_index -lt $_argc_len ]]; do
+            _argc_take_value="${argc__args[_argc_take_index]}"
+            if _argc_maybe_flag_option "$signs" "$_argc_take_value"; then
+                if [[ "${#_argc_take_value}" -gt 1 ]]; then
+                    break
+                fi
+            fi
+            _argc_take_args_values+=("$_argc_take_value")
+            _argc_take_args_len=$((_argc_take_args_len + 1))
+            if [[ "$_argc_take_args_len" -ge "$max" ]]; then
+                break
+            fi
+            _argc_take_index=$((_argc_take_index + 1))
+        done
+    fi
+    if [[ "${#_argc_take_args_values[@]}" -lt "$min" ]]; then
+        _argc_die "error: incorrect number of values for \`$param\`"
+    fi
+    if [[ -n "$delimiter" ]] && [[ "${#_argc_take_args_values[@]}" -gt 0 ]]; then
+        local item values arr=()
+        for item in "${_argc_take_args_values[@]}"; do
+            IFS="$delimiter" read -r -a values <<<"$item"
+            arr+=("${values[@]}")
+        done
+        _argc_take_args_values=("${arr[@]}")
+    fi
+}
+
+_argc_maybe_flag_option() {
+    local signs="$1" arg="$2"
+    if [[ -z "$signs" ]]; then
+        return 1
+    fi
+    local cond=false
+    if [[ "$signs" == *"+"* ]]; then
+        if [[ "$arg" =~ ^\+[^+].* ]]; then
+            cond=true
+        fi
+    elif [[ "$arg" == -* ]]; then
+        if (( ${#arg} < 3 )) || [[ ! "$arg" =~ ^---.* ]]; then
+            cond=true
+        fi
+    fi
+    if [[ "$cond" == "false" ]]; then
+        return 1
+    fi
+    local value="${arg%%=*}"
+    if [[ "$value" =~ [[:space:]] ]]; then
+        return 1
+    fi
+    return 0
+}
+
+_argc_die() {
+    if [[ $# -eq 0 ]]; then
+        cat
+    else
+        echo "$*" >&2
+    fi
+    exit 1
+}
+
+_argc_run "$@"
+
+# ARGC-BUILD }

assets/agents/coder/README.md

@@ -1,16 +1,82 @@
 # Coder
 
-An AI agent that assists you with your coding tasks.
+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.
 
-This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent to implement code specifications. Sisyphus 
-acts as the coordinator/architect, while Coder handles the implementation details.
+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.
 
-## Features
+## Workflow
 
-- 🏗️ Intelligent project structure creation and management
-- 🖼️ Convert screenshots into clean, functional code
-- 📁 Comprehensive file system operations (create folders, files, read/write files)
-- 🧐 Advanced code analysis and improvement suggestions
-- 📊 Precise diff-based file editing for controlled code modifications
+```
+analyze_request (llm + output_schema)   plan + complexity extraction
+        ↓
+route_complexity (script)               opt-out approval gate (complexity ≥ 7)
+        ↓
+gate_approval (approval, optional)
+        ↓
+implement (llm + fs tools)              actual file edits
+        ↓
+verify_build (script)
+        ↓
+verify_tests (script)
+        ↓
+fix_loop_gate (script)                  back-edge to implement (bounded)
+        ↓
+end_success / end_rejected / end_failure
+```
 
-It can also be used as a standalone tool for direct coding assistance.
+End nodes emit one of three sentinel outcomes for the caller:
+
+- `CODER_COMPLETE` — build and tests passed.
+- `CODER_REJECTED` — user rejected the plan at the approval gate.
+- `CODER_FAILED` — fix-loop exhausted; build/tests still failing.
+
+## Tuning
+
+The agent's `project_dir` is exposed via the standard `variables:` block,
+so it accepts the runtime override flag:
+
+```sh
+# Invoke from inside the project (project_dir defaults to ".")
+cd /path/to/your/project
+coyote -a coder "Add a foo() function..."
+
+# Or invoke from anywhere with an explicit override
+coyote -a coder --agent-variable project_dir /path/to/your/project "Add..."
+```
+
+`graph.yaml` `initial_state` exposes:
+
+- `max_fix_attempts` (default `3`) — fix-loop budget before `end_failure`.
+
+Environment overrides honored by the script nodes:
+
+- `BUILD_CMD` — skip project-type detection for the build/check command.
+- `TEST_CMD` — skip detection for tests.
+- `CODER_AUTOAPPROVE=1` — bypass the approval gate (for non-interactive runs
+  where complexity might trip the gate).
+
+## Pro-Tip: IDE MCP Server
+
+Modern IDEs (JetBrains, VS Code, Cursor, Zed, etc.) expose MCP servers
+that let LLMs use IDE tools directly. To wire one in, edit `graph.yaml`:
+
+```yaml
+mcp_servers:
+  - your-ide-mcp-server
+
+global_tools:
+  # Keep read-only fs tools for files outside the IDE project
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+#  - fs_write.sh
+#  - fs_patch.sh
+  - execute_command.sh
+```
+
+Then add the MCP server's write/patch tools to the `implement` node's
+`tools:` whitelist.

assets/agents/coder/config.yaml

@@ -1,105 +0,0 @@
-name: coder
-description: Implementation agent - writes code, follows patterns, verifies with builds
-version: 1.0.0
-temperature: 0.1
-top_p: 0.95
-
-auto_continue: true
-max_auto_continues: 15
-inject_todo_instructions: true
-
-variables:
-  - name: project_dir
-    description: Project directory to work in
-    default: '.'
-
-global_tools:
-  - fs_read.sh
-  - fs_grep.sh
-  - fs_glob.sh
-  - fs_write.sh
-  - fs_patch.sh
-  - execute_command.sh
-
-instructions: |
-  You are a senior engineer. You write code that works on the first try.
-
-  ## Your Mission
-
-  Given an implementation task:
-  1. Understand what to build (from context provided)
-  2. Study existing patterns (read 1-2 similar files)
-  3. Write the code (using tools, NOT chat output)
-  4. Verify it compiles/builds
-  5. Signal completion
-
-  ## Todo System
-
-  For multi-file changes:
-  1. `todo__init` with the implementation goal
-  2. `todo__add` for each file to create/modify
-  3. Implement each, calling `todo__done` immediately after
-
-  ## Writing Code
-
-  **CRITICAL**: Write code using `write_file` tool, NEVER paste code in chat.
-
-  Correct:
-  ```
-  write_file --path "src/user.rs" --content "pub struct User { ... }"
-  ```
-
-  Wrong:
-  ```
-  Here's the implementation:
-  \`\`\`rust
-  pub struct User { ... }
-  \`\`\`
-  ```
-
-  ## File Reading Strategy (IMPORTANT - minimize token usage)
-
-  1. **Use grep to find relevant code** - `fs_grep --pattern "fn handle_request" --include "*.rs"` finds where things are
-  2. **Read only what you need** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79
-  3. **Never cat entire large files** - If 500+ lines, read the relevant section after grepping for it
-  4. **Use glob to find files** - `fs_glob --pattern "*.rs" --path src/` discovers files by name
-
-  ## Pattern Matching
-
-  Before writing ANY file:
-  1. Find a similar existing file (use `fs_grep` to locate, then `fs_read` to examine)
-  2. Match its style: imports, naming, structure
-  3. Follow the same patterns exactly
-
-  ## Verification
-
-  After writing files:
-  1. Run `verify_build` to check compilation
-  2. If it fails, fix the error (minimal change)
-  3. Don't move on until build passes
-
-  ## Completion Signal
-
-  End with:
-  ```
-  CODER_COMPLETE: [summary of what was implemented]
-  ```
-
-  Or if failed:
-  ```
-  CODER_FAILED: [what went wrong]
-  ```
-
-  ## Rules
-
-  1. **Write code via tools** - Never output code to chat
-  2. **Follow patterns** - Read existing files first
-  3. **Verify builds** - Don't finish without checking
-  4. **Minimal fixes** - If build fails, fix precisely
-  5. **No refactoring** - Only implement what's asked
-
-  ## Context
-  - Project: {{project_dir}}
-  - CWD: {{__cwd__}}
-  - Shell: {{__shell__}}
-

assets/agents/coder/graph.yaml

@@ -0,0 +1,375 @@
+name: coder
+description: |
+  Implementation agent. Plans, implements, and runs build + tests in a
+  bounded fix-loop until verified. 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:
+  - 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 `coyote` from. Override at runtime with
+      `coyote -a coder --agent-variable project_dir /abs/path "..."`.
+    default: "."
+
+settings:
+  max_loop_iterations: 20
+  log_state_snapshots: true
+  validate_before_run: true
+  timeout: 1800
+
+initial_state:
+  project_dir: ""
+  fix_attempts: 0
+  max_fix_attempts: 3
+  fix_instructions: ""
+  build_output: ""
+  tests_output: ""
+  last_node_output: ""
+  plan_summary: ""
+  files_to_modify: []
+  files_to_create: []
+  risks: []
+  complexity_score: 0
+  review_attempts: 0
+  max_review_attempts: 1
+  review_clean: true
+  review_notes: ""
+
+start: resolve_paths
+
+nodes:
+  resolve_paths:
+    id: resolve_paths
+    type: script
+    description: Resolve project_dir to an absolute path from the agent variable
+    script: scripts/resolve_paths.sh
+    timeout: 5
+    fallback: end_failure
+
+  analyze_request:
+    id: analyze_request
+    type: llm
+    description: Extract a structured plan and complexity score from the orchestrator's prompt
+    instructions: |
+      You are a senior engineer's planning assistant. Read the orchestrator's
+      request and emit a structured plan. You only plan. You never edit files.
+
+      Score complexity from 1 to 10:
+        1-3: trivial - single file, <=20 lines changed, obvious approach
+        4-6: moderate - 2-5 files, clear approach, some pattern matching
+        7-10: complex - multi-component, ambiguous tradeoffs, refactoring,
+              or wide blast radius
+
+      Be specific in `files_to_modify` and `files_to_create`. All paths
+      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 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
+      implementation: unknown dependencies, brittle tests, blast radius,
+      etc. Empty list is fine.
+
+      Project directory: {{project_dir}}
+    prompt: "{{initial_prompt}}"
+    tools: []
+    output_schema:
+      type: object
+      properties:
+        plan_summary:
+          type: string
+          description: 1-3 sentences summarizing what will be done
+        files_to_modify:
+          type: array
+          items: {type: string}
+        files_to_create:
+          type: array
+          items: {type: string}
+        complexity_score:
+          type: integer
+          minimum: 1
+          maximum: 10
+        risks:
+          type: array
+          items: {type: string}
+      required: [plan_summary, files_to_modify, files_to_create, complexity_score, risks]
+    state_updates:
+      last_node_output: "{{output}}"
+    fallback: end_failure
+    next: route_complexity
+
+  route_complexity:
+    id: route_complexity
+    type: script
+    description: Route to approval gate for complex plans; skip otherwise
+    script: scripts/route_complexity.sh
+    timeout: 5
+    fallback: implement
+
+  gate_approval:
+    id: gate_approval
+    type: approval
+    description: Optional human checkpoint for high-complexity plans
+    question: |
+      ## Plan
+      {{plan_summary}}
+
+      ## Files to modify
+      {{files_to_modify}}
+
+      ## Files to create
+      {{files_to_create}}
+
+      ## Risks
+      {{risks}}
+
+      Complexity: {{complexity_score}}/10
+
+      Approve this plan?
+    options:
+      - "yes"
+      - "no"
+    routes:
+      "yes": implement
+      "no": end_rejected
+    on_other: end_rejected
+
+  implement:
+    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 write files via `execute_command`. Do not use `cat >`,
+         `cat >>`, `echo >`, `printf >`, `tee`, heredocs (`<<EOF`), or
+         `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}}.
+
+      ## File reading
+
+      1. Use `execute_command` to grep/find:
+         `execute_command --command "grep -rn 'fn handle_request' --include='*.rs' ."`
+         `execute_command --command "find . -name '*.rs' -not -path '*/target/*'"`
+      2. Read only what you need:
+         `fs_cat --path "src/main.rs" --offset 50 --limit 30`
+      3. Never read entire large files. Use offset/limit.
+      4. Use `fs_ls` to list directory contents.
+
+      ## Pattern matching
+
+      Before writing ANY file:
+      1. Find a similar existing file (grep, then read).
+      2. Match its style: imports, naming, structure, error handling.
+      3. Follow the same patterns exactly. Do not invent new ones.
+
+      ## Fix loop
+
+      If the "Fix loop status" section in your user prompt is non-empty,
+      the previous attempt failed verification. Read the error, identify
+      the minimal fix, apply it. Do not refactor while fixing.
+
+      ## Rules
+
+      1. Match existing patterns - read examples first.
+      2. Minimal changes - implement only what's asked.
+      3. Never suppress errors (`as any`, `@ts-ignore`, `#[allow(...)]`
+         on unfamiliar lints, etc.).
+      4. No dead code, no commented-out blocks, no premature abstractions.
+      5. End your turn when editing is done. The graph runs verification next.
+
+      Project directory: {{project_dir}}
+    prompt: |
+      ## Plan summary
+      {{plan_summary}}
+
+      ## Files involved
+      - Modify: {{files_to_modify}}
+      - Create: {{files_to_create}}
+
+      ## Original request from the orchestrator
+      {{initial_prompt}}
+
+      ## Fix loop status
+      {{fix_instructions}}
+    tools:
+      - fs_cat
+      - fs_ls
+      - fs_write
+      - fs_patch
+      - execute_command
+    max_iterations: 30
+    state_updates:
+      last_node_output: "{{output}}"
+    fallback: end_failure
+    next: verify_build
+
+  verify_build:
+    id: verify_build
+    type: script
+    description: Run the project's check/build command. Routes to verify_tests on success, fix_loop_gate on failure.
+    script: scripts/verify_build.sh
+    timeout: 300
+    fallback: fix_loop_gate
+
+  verify_tests:
+    id: verify_tests
+    type: script
+    description: Run the project's test command. Routes to end_success on pass, fix_loop_gate on failure.
+    script: scripts/verify_tests.sh
+    timeout: 600
+    fallback: fix_loop_gate
+
+  fix_loop_gate:
+    id: fix_loop_gate
+    type: script
+    description: Budget gate. Loops back to implement with fix_instructions populated, or terminates as end_failure.
+    script: scripts/fix_loop_gate.sh
+    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
+    output: |
+      CODER_COMPLETE
+      Plan: {{plan_summary}}
+      Files modified: {{files_to_modify}}
+      Files created: {{files_to_create}}
+      Build: passed
+      Tests: passed
+
+  end_rejected:
+    id: end_rejected
+    type: end
+    output: |
+      CODER_REJECTED
+      Plan was rejected at the approval gate.
+      Plan: {{plan_summary}}
+
+  end_failure:
+    id: end_failure
+    type: end
+    output: |
+      CODER_FAILED
+      Plan: {{plan_summary}}
+      Attempts: {{fix_attempts}}/{{max_fix_attempts}}
+
+      Last node output:
+      {{last_node_output}}
+
+      Last build output:
+      {{build_output}}
+
+      Last tests output:
+      {{tests_output}}

assets/agents/coder/scripts/fix_loop_gate.sh

@@ -0,0 +1,49 @@
+#!/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 "$state" | jq -r '.max_fix_attempts // 3')
+build_ok=$(echo "$state" | jq -r '.build_ok | if . == null then "true" else (. | tostring) end')
+tests_ok=$(echo "$state" | jq -r '.tests_ok | if . == null then "true" else (. | tostring) end')
+build_output=$(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 [[ "$build_ok" != "true" ]]; then
+  fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nThe previous attempt failed the build.\n\nBuild output:\n```\n%s\n```\n\nIdentify the minimal fix and apply it. Do not refactor.' \
+    "$next_attempts" "$max_fix_attempts" "$build_output")
+elif [[ "$tests_ok" != "true" ]]; then
+  fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nBuild passed but tests failed.\n\nTest output:\n```\n%s\n```\n\nIdentify the minimal fix and apply it. Do not refactor.' \
+    "$next_attempts" "$max_fix_attempts" "$tests_output")
+else
+  fix_instructions=$(printf '## Fix loop status (attempt %d of %d)\n\nfix_loop_gate was reached but no failure was detected in state. Re-run the verification step.' \
+    "$next_attempts" "$max_fix_attempts")
+fi
+
+jq -nc \
+  --argjson n "$next_attempts" \
+  --arg fi "$fix_instructions" \
+  '{
+    "fix_attempts": $n,
+    "fix_instructions": $fi,
+    "_next": "implement"
+  }'

assets/agents/coder/scripts/resolve_paths.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+project_dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
+resolved=$(cd "$project_dir" 2>/dev/null && pwd) || resolved="$project_dir"
+
+jq -nc \
+  --arg pd "$resolved" \
+  '{
+    "project_dir": $pd,
+    "_next": "analyze_request"
+  }'

assets/agents/coder/scripts/route_complexity.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="$GRAPH_STATE"
+else
+  state='{}'
+fi
+
+complexity=$(echo "$state" | jq -r '.complexity_score // 0')
+
+if [[ "${CODER_AUTOAPPROVE:-0}" == "1" ]]; then
+  jq -nc '{"_next": "implement"}'
+  exit 0
+fi
+
+if (( complexity >= 7 )); then
+  jq -nc '{"_next": "gate_approval"}'
+else
+  jq -nc '{"_next": "implement"}'
+fi

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_build.sh

@@ -0,0 +1,55 @@
+#!/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 "$output" \
+    --arg cmd "$cmd" \
+    '{
+      "build_ok": true,
+      "build_output": ("Ran: " + $cmd + "\n\n" + $out),
+      "_next": "verify_tests"
+    }'
+else
+  jq -nc \
+    --arg out "$output" \
+    --arg cmd "$cmd" \
+    --argjson rc "$exit_code" \
+    '{
+      "build_ok": false,
+      "build_output": ("Ran: " + $cmd + "\nExit code: " + ($rc | tostring) + "\n\n" + $out),
+      "_next": "fix_loop_gate"
+    }'
+fi

assets/agents/coder/scripts/verify_tests.sh

@@ -0,0 +1,55 @@
+#!/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": "self_review"
+  }'
+  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 "$output" \
+    --arg cmd "$cmd" \
+    '{
+      "tests_ok": true,
+      "tests_output": ("Ran: " + $cmd + "\n\n" + $out),
+      "_next": "self_review"
+    }'
+else
+  jq -nc \
+    --arg out "$output" \
+    --arg cmd "$cmd" \
+    --argjson rc "$exit_code" \
+    '{
+      "tests_ok": false,
+      "tests_output": ("Ran: " + $cmd + "\nExit code: " + ($rc | tostring) + "\n\n" + $out),
+      "_next": "fix_loop_gate"
+    }'
+fi

assets/agents/coder/tools.sh

@@ -14,80 +14,6 @@ _project_dir() {
   (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
 }
 
-# @cmd Read a file's contents before modifying
-# @option --path! Path to the file (relative to project root)
-read_file() {
-	# shellcheck disable=SC2154
-  local file_path="${argc_path}"
-  local project_dir
-  project_dir=$(_project_dir)
-  local full_path="${project_dir}/${file_path}"
-  
-  if [[ ! -f "${full_path}" ]]; then
-    warn "File not found: ${file_path}" >> "$LLM_OUTPUT"
-    return 0
-  fi
-  
-  {
-  	info "Reading: ${file_path}"
-  	echo ""
-  	cat "${full_path}"
-  } >> "$LLM_OUTPUT"
-}
-
-# @cmd Write complete file contents
-# @option --path! Path for the file (relative to project root)
-# @option --content! Complete file contents to write
-write_file() {
-  local file_path="${argc_path}"
-  # shellcheck disable=SC2154
-  local content="${argc_content}"
-  local project_dir
-  project_dir=$(_project_dir)
-  local full_path="${project_dir}/${file_path}"
-  
-  mkdir -p "$(dirname "${full_path}")"
-  echo "${content}" > "${full_path}"
-  
-  green "Wrote: ${file_path}" >> "$LLM_OUTPUT"
-}
-
-# @cmd Find files similar to a given path (for pattern matching)
-# @option --path! Path to find similar files for
-find_similar_files() {
-  local file_path="${argc_path}"
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  local ext="${file_path##*.}"
-  local dir
-  dir=$(dirname "${file_path}")
-  
-  info "Similar files to: ${file_path}" >> "$LLM_OUTPUT"
-  echo "" >> "$LLM_OUTPUT"
-  
-  local results
-  results=$(find "${project_dir}/${dir}" -maxdepth 1 -type f -name "*.${ext}" \
-    ! -name "$(basename "${file_path}")" \
-    ! -name "*test*" \
-    ! -name "*spec*" \
-    2>/dev/null | head -3)
-  
-  if [[ -z "${results}" ]]; then
-    results=$(find "${project_dir}/src" -type f -name "*.${ext}" \
-      ! -name "*test*" \
-      ! -name "*spec*" \
-      -not -path '*/target/*' \
-      2>/dev/null | head -3)
-  fi
-  
-  if [[ -n "${results}" ]]; then
-    echo "${results}" >> "$LLM_OUTPUT"
-  else
-    warn "No similar files found" >> "$LLM_OUTPUT"
-  fi
-}
-
 # @cmd Verify the project builds successfully
 verify_build() {
   local project_dir
@@ -170,27 +96,3 @@ get_project_structure() {
   } >> "$LLM_OUTPUT"
 }
 
-# @cmd Search for content in the codebase
-# @option --pattern! Pattern to search for
-search_code() {
-	# shellcheck disable=SC2154
-  local pattern="${argc_pattern}"
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  info "Searching: ${pattern}" >> "$LLM_OUTPUT"
-  echo "" >> "$LLM_OUTPUT"
-  
-  local results
-  results=$(grep -rn "${pattern}" "${project_dir}" 2>/dev/null | \
-    grep -v '/target/' | \
-    grep -v '/node_modules/' | \
-    grep -v '/.git/' | \
-    head -20) || true
-  
-  if [[ -n "${results}" ]]; then
-    echo "${results}" >> "$LLM_OUTPUT"
-  else
-    warn "No matches" >> "$LLM_OUTPUT"
-  fi
-}

assets/agents/deep-research/README.md

@@ -0,0 +1,274 @@
+# deep-research
+
+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
+revise weak findings, delegates the final write-up to a focused
+sub-agent, checks that the cited sources are reachable, and gates the
+result behind human approval.
+
+Unlike a regular agent (which takes a goal and improvises the steps),
+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 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/coyote/wiki/Graph-Agents).
+
+## Workflow
+
+17 nodes. `->` is the static route; a script node can also route
+dynamically via `_next`. The `▶▶` line is a parallel super-step —
+those branches run concurrently:
+
+```
+parse_request (script)              -> bootstrap_research   (or -> ask_topic if no topic)
+ask_topic (input)                   -> bootstrap_research
+bootstrap_research (script)         -> [plan, knowledge_lookup]   ▶▶ parallel
+plan (llm + output_schema)          -> research_each_question
+knowledge_lookup (rag)              -> research_each_question
+research_each_question (map)        -> combine_findings    (spawns one branch per question)
+  └─ research_one_question (llm)    (atomic; runs N×, joins at map)
+combine_findings (script)           -> vet_sources
+vet_sources (llm + custom tool)     -> critique
+critique (llm)                      -> reflexion_gate
+reflexion_gate (script)             -> synthesize  (or -> research_each_question: reflexion loop)
+synthesize (agent: report-writer)   -> verify_sources
+verify_sources (script)             -> approve
+approve (approval)                  -> end_accepted          ("accept")
+                                    -> end_rejected          ("reject")
+                                    -> incorporate_feedback   (any free-form answer)
+incorporate_feedback (script)       -> research_each_question (the human-feedback loop)
+```
+
+### Node-type breakdown
+
+| Type                        | Nodes                                                                                                                 |
+|-----------------------------|-----------------------------------------------------------------------------------------------------------------------|
+| `script` (Python)           | `parse_request`, `bootstrap_research`, `combine_findings`, `reflexion_gate`, `verify_sources`, `incorporate_feedback` |
+| `llm` (tools: `[]`)         | `plan`, `critique`                                                                                                    |
+| `llm` (with tool whitelist) | `research_one_question`, `vet_sources`                                                                                |
+| `rag`                       | `knowledge_lookup` — local corpus retrieval                                                                           |
+| `map`                       | `research_each_question` — dynamic fan-out per sub-question                                                           |
+| `agent`                     | `synthesize` — spawns the `report-writer` sub-agent                                                                   |
+| `input`                     | `ask_topic`                                                                                                           |
+| `approval`                  | `approve`                                                                                                             |
+| `end`                       | `end_accepted`, `end_rejected`                                                                                        |
+
+## Parallel execution
+
+The graph has two parallel super-steps where Coyote's BSP scheduler runs
+branches concurrently.
+
+**1. Context loading (`plan` ‖ `knowledge_lookup`)** — after
+`bootstrap_research`, the LLM planner (which decomposes the topic into
+sub-questions) and the RAG retrieval over the local `knowledge/`
+corpus run side by side. They write disjoint state keys (`plan` writes
+`research_plan` and `questions`; `knowledge_lookup` writes
+`local_context` and `local_sources`) so no reducer is needed.
+
+**2. Per-question research (`research_each_question` map)** — the
+plan emits a `questions` array (3-5 entries, enforced by its
+`output_schema`). The `map` node spawns one parallel branch per
+question (`max_concurrency: 3`). Each branch is an isolated
+`research_one_question` LLM invocation with web tools, instructed to
+investigate exactly its assigned question. Outputs collect into
+`question_findings` in input order, then `combine_findings` joins
+them into a single `findings` Markdown document for downstream nodes.
+
+`settings.max_concurrency: 4` is the graph-wide cap; the per-`map`
+override (`max_concurrency: 3` on `research_each_question`) is
+deliberately lower to leave headroom for the planner's tool calls
+running alongside RAG.
+
+## Local knowledge corpus
+
+`knowledge_lookup` is a `rag` node — it runs hybrid (vector + keyword)
+retrieval over every file in `knowledge/`. The directory ships with a
+small `research-style-notes.md` so the RAG node has something to
+retrieve against on a clean install; drop your own Markdown notes,
+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/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
+rebuild.
+
+## Sub-agent: report-writer
+
+The `synthesize` node is an `agent` node that spawns the
+`report-writer` sub-agent (`assets/agents/report-writer/`). This is
+the agent-as-tool pattern: the orchestrating graph delegates the
+writing phase to a focused sub-agent dedicated to coherent prose,
+while the research phase uses different (typically cheaper) LLM nodes
+for fast-and-many-question investigation.
+
+The `report-writer` sub-agent has no tools — it cannot access the
+web, cannot search, and cannot invent facts. It reads only the
+findings it is given and produces a final Markdown report preserving
+every inline citation. See `assets/agents/report-writer/README.md`
+for details.
+
+## Tools and tool scoping
+
+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_coyote`,
+  `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
+  deterministic source-credibility classifier shipped with this agent.
+
+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               |
+|-------------------------|-----------------------------------------------------------------------------|--------------------------|
+| `plan`, `critique`      | `[]`                                                                        | nothing - pure reasoning |
+| `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     |
+
+`research_one_question` (each parallel branch of the map) can search
+and fetch but cannot classify sources; `vet_sources` can classify
+sources but cannot touch the web. That separation is the point of the
+`tools:` whitelist: a node gets only the tools its job calls for,
+never the agent's full set.
+
+The `classify_source` custom tool (`tools.sh`) takes a URL and returns
+a credibility tier (government, academic, preprint, organization,
+unverified) derived from the host and top-level domain. It is
+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/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 Coyote's
+default MCP servers; make sure it is registered in
+`~/.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 `coyote agents install`; if you install one manually,
+install both so the agent reference resolves.
+
+## Reflexion
+
+The agent has two loops, both built with script nodes that route via
+`_next`. The engine allows back-edges at runtime; the validator only
+rejects cycles built from static `next` / `routes` edges, so script
+`_next` loops are always allowed.
+
+**Automated reflexion loop.** After the parallel research map and
+`vet_sources`, the `critique` node reviews the merged findings
+against the research plan and the source credibility assessment, and
+emits `VERDICT: PASS` or `VERDICT: REVISE` with specific feedback.
+`reflexion_gate.py` then:
+
+- `PASS` -> continue to `synthesize`.
+- `REVISE`, budget remaining -> loop back to `research_each_question`,
+  with the critique injected as `research_feedback` so every parallel
+  branch sees it on the retry.
+- `REVISE`, budget spent -> continue to `synthesize` anyway (the human
+  approval step is the final backstop).
+
+The budget is `MAX_REFLEXION_REVISIONS` in `reflexion_gate.py`
+(default 2, so the research map runs at most 3 times per pass).
+
+**Human-feedback loop.** At `approve` the user answers `accept`,
+`reject`, or types their own feedback. A free-form answer routes via
+the approval node's `on_other` to `incorporate_feedback.py`, which
+folds that text into `research_feedback` and loops back to
+`research_each_question` for another parallel pass.
+
+`settings.max_loop_iterations` (40) is the engine's infinite-loop
+backstop: it caps the total visits to any single node.
+
+## Running
+
+```sh
+coyote agents install                  # ships deep-research
+coyote -a deep-research "How does HTTP/3 differ from HTTP/2?"
+coyote -a deep-research "Recent advances in solid-state batteries"
+coyote -a deep-research                # no prompt -> triggers ask_topic
+```
+
+## Anti-hallucination
+
+- `research_one_question` (each map branch) is instructed to back
+  every claim with a real retrieved source and never to fabricate
+  URLs, titles, or DOIs.
+- `vet_sources` classifies every cited source so weak sources are
+  visible to the critique step.
+- `critique` independently reviews the merged findings and sends weak
+  or uncited work back for another parallel research pass.
+- `synthesize` (the `report-writer` sub-agent) is grounded: it may use
+  only the gathered findings and must keep each claim's inline source.
+  It has no tools and cannot browse the web.
+- `verify_sources` probes every cited URL / DOI with an HTTP HEAD
+  request and reports which are unreachable, so the human reviewer
+  sees broken citations before approving.
+
+## Customizing
+
+- **Loop budget.** `MAX_REFLEXION_REVISIONS` in `reflexion_gate.py`.
+- **Map concurrency.** The `research_each_question` node's
+  `max_concurrency: 3` caps simultaneous web-research branches.
+  Raise to investigate more questions in parallel; lower to be gentle
+  on rate-limited providers.
+- **Per-node model.** Add `model: anthropic:...` to any `llm` node.
+  Cheap models work well for `plan` / `critique` / `vet_sources`; the
+  heavy intelligence is needed in `research_one_question` and the
+  `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_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
+  knowledge corpus* section above).
+- **Different writer.** Replace `agent: report-writer` on the
+  `synthesize` node with the name of any other agent. The
+  orchestrator does not care what kind of agent the writer is.
+- **Skip approval.** Point both `approve` routes at `end_accepted`,
+  or wire `verify_sources` straight to an `end` node.
+
+## Files
+
+```
+assets/agents/deep-research/
+  graph.yaml                    - agent config + 17-node workflow
+  tools.sh                      - classify_source custom tool
+  README.md                     - this file
+  knowledge/
+    README.md                   - corpus-format notes
+    research-style-notes.md     - starter knowledge file (replace with your notes)
+  scripts/
+    parse_request.py            - _next: bootstrap_research, or ask_topic if no topic
+    bootstrap_research.py       - fan-out source: next [plan, knowledge_lookup]
+    combine_findings.py         - joins map output (question_findings) into findings
+    reflexion_gate.py           - _next: research_each_question (revise) or synthesize
+    verify_sources.py           - HTTP HEAD on cited URLs / DOIs
+    incorporate_feedback.py     - _next: research_each_question, with user feedback
+```
+
+See also `assets/agents/report-writer/` — the sub-agent the
+`synthesize` node spawns.

assets/agents/deep-research/graph.yaml

@@ -0,0 +1,291 @@
+name: deep-research
+description: |
+  Deep web research workflow. 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 revise weak or incomplete findings,
+  delegates the final write-up to a focused sub-agent, checks that the
+  cited sources are reachable, and gates the result behind human
+  approval. A reviewer's free-form feedback at the approval step feeds
+  back into another research pass.
+
+  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"
+
+global_tools:
+  - web_search_coyote.sh
+  - fetch_url_via_curl.sh
+  - search_arxiv.sh
+
+mcp_servers:
+  - ddg-search
+
+conversation_starters:
+  - "How does HTTP/3 differ from HTTP/2?"
+  - "Summarize recent advances in solid-state battery chemistry"
+
+settings:
+  max_loop_iterations: 40
+  log_state_snapshots: false
+  validate_before_run: true
+  max_concurrency: 4
+
+initial_state:
+  research_feedback: ""
+  research_attempts: 0
+  local_context: ""
+  local_sources: ""
+
+start: parse_request
+
+nodes:
+
+  parse_request:
+    id: parse_request
+    type: script
+    script: scripts/parse_request.py
+    next: bootstrap_research
+
+  ask_topic:
+    id: ask_topic
+    type: input
+    question: "What would you like me to research?"
+    validation: "len(input) > 0"
+    state_updates:
+      topic: "{{input}}"
+    next: bootstrap_research
+
+  bootstrap_research:
+    id: bootstrap_research
+    type: script
+    script: scripts/bootstrap_research.py
+    next: [plan, knowledge_lookup]
+
+  plan:
+    id: plan
+    type: llm
+    instructions: |
+      You are a research planner. Given a topic, produce a focused
+      research plan and decompose it into 3-5 specific sub-questions
+      that can each be researched independently in parallel.
+
+      The plan is a short narrative naming the key questions and the
+      kinds of sources that would be authoritative. The sub-questions
+      are precise, self-contained queries (each one is sent on its own
+      to a separate research worker, so they must be answerable
+      without each other's context).
+    prompt: "Research topic: {{topic}}"
+    tools: []
+    output_schema:
+      type: object
+      properties:
+        research_plan:
+          type: string
+          description: A short plan narrative.
+        questions:
+          type: array
+          items: { type: string }
+          minItems: 1
+          maxItems: 6
+          description: 3-5 specific, self-contained sub-questions.
+      required: [research_plan, questions]
+    next: research_each_question
+
+  knowledge_lookup:
+    id: knowledge_lookup
+    type: rag
+    documents:
+      - ./knowledge/
+    query: "{{topic}}"
+    top_k: 6
+    chunk_size: 1000
+    chunk_overlap: 100
+    state_updates:
+      local_context: "{{output.context}}"
+      local_sources: "{{output.sources}}"
+    next: research_each_question
+
+  research_each_question:
+    id: research_each_question
+    type: map
+    over: "{{questions}}"
+    as: question
+    branch: research_one_question
+    collect_into: question_findings
+    max_concurrency: 3
+    next: combine_findings
+
+  research_one_question:
+    id: research_one_question
+    type: llm
+    instructions: |
+      You are a web research assistant. Investigate the SINGLE question
+      given to you using your tools: search the web, fetch and read
+      pages, and search arXiv for academic sources.
+
+      Rules:
+        - Every factual claim must be backed by a real source you
+          actually retrieved. Never fabricate URLs, page titles,
+          authors, or DOIs.
+        - Prefer primary and authoritative sources over aggregators.
+        - Where sources disagree, report the disagreement rather than
+          papering over it.
+        - Put the URL (or DOI) inline next to each claim it supports.
+
+      Return organized findings in plain text. Do not include
+      meta-commentary about the process.
+    prompt: |
+      Research question: {{question}}
+
+      Local context that may help:
+      {{local_context}}
+
+      {{research_feedback}}
+    tools:
+      - web_search_coyote
+      - fetch_url_via_curl
+      - search_arxiv
+      - mcp:ddg-search
+    max_iterations: 10
+    max_attempts: 2
+    temperature: 0.1
+
+  combine_findings:
+    id: combine_findings
+    type: script
+    script: scripts/combine_findings.py
+    next: vet_sources
+
+  vet_sources:
+    id: vet_sources
+    type: llm
+    instructions: |
+      You assess the credibility of the sources cited in a set of
+      research findings. For every distinct source URL in the findings,
+      call the `classify_source` tool to get its credibility tier. Then
+      summarize: which claims rest on HIGH-credibility sources, and
+      which rest on PREPRINT or UNVERIFIED sources and so need
+      corroboration. Do NOT do any new research -- assess only what is
+      already cited.
+    prompt: |
+      Findings to assess:
+      {{findings}}
+    tools:
+      - classify_source
+    max_iterations: 15
+    state_updates:
+      source_assessment: "{{output}}"
+    next: critique
+
+  critique:
+    id: critique
+    type: llm
+    instructions: |
+      You are a meticulous research reviewer. Judge whether the
+      findings below are good enough to synthesize a complete,
+      well-supported report that answers the research plan.
+
+      Mark the findings REVISE if ANY of these hold:
+        - A research-plan question is unanswered or only weakly
+          addressed.
+        - A factual claim has no source, or cites a source that looks
+          fabricated.
+        - The findings lean on a single source where corroboration is
+          needed.
+        - A key claim rests only on a PREPRINT or UNVERIFIED source,
+          per the source credibility assessment below.
+        - An obvious counter-perspective or recent development is
+          missing.
+      Otherwise mark them PASS.
+
+      Respond in EXACTLY this format, nothing else:
+
+      VERDICT: <PASS or REVISE>
+      FEEDBACK: <if REVISE, be specific and actionable -- name the gaps
+      and what kind of source would close them; if PASS, write "none">
+    prompt: |
+      Research plan:
+      {{research_plan}}
+
+      Findings under review:
+      {{findings}}
+
+      Source credibility assessment:
+      {{source_assessment}}
+    tools: []
+    state_updates:
+      critique: "{{output}}"
+    next: reflexion_gate
+
+  reflexion_gate:
+    id: reflexion_gate
+    type: script
+    script: scripts/reflexion_gate.py
+    next: synthesize
+
+  synthesize:
+    id: synthesize
+    type: agent
+    agent: report-writer
+    prompt: |
+      Research topic: {{topic}}
+
+      Findings (organized by sub-question, with inline citations):
+      {{findings}}
+
+      Source credibility assessment:
+      {{source_assessment}}
+
+      Produce the final report following your instructions.
+    timeout: 300
+    state_updates:
+      report: "{{output}}"
+    next: verify_sources
+
+  verify_sources:
+    id: verify_sources
+    type: script
+    script: scripts/verify_sources.py
+    next: approve
+
+  approve:
+    id: approve
+    type: approval
+    question: |
+      Research report on: {{topic}}
+
+      {{report}}
+
+      ----
+      {{source_check}}
+      ----
+
+      Accept this report? Pick "accept" or "reject", or type specific
+      feedback to send the research back for another pass.
+    options:
+      - "accept"
+      - "reject"
+    routes:
+      "accept": end_accepted
+      "reject": end_rejected
+    on_other: incorporate_feedback
+    state_updates:
+      decision: "{{choice}}"
+
+  incorporate_feedback:
+    id: incorporate_feedback
+    type: script
+    script: scripts/incorporate_feedback.py
+
+  end_accepted:
+    id: end_accepted
+    type: end
+    output: "{{report}}"
+
+  end_rejected:
+    id: end_rejected
+    type: end
+    output: "Research on '{{topic}}' was rejected and discarded."

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

@@ -0,0 +1,23 @@
+# Local knowledge corpus for deep-research
+
+The `knowledge_lookup` node in `graph.yaml` is a `rag` node that runs
+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.
+
+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
+node has something non-empty to retrieve against on a clean install.
+Replace or extend it with your own materials to bias the research
+phase toward your local context.
+
+To force the knowledge base to rebuild after you add or change files,
+delete the cached index:
+
+```sh
+rm ~/.config/coyote/agents/deep-research/knowledge_lookup.yaml
+```
+
+The next run will rebuild from the current contents of this directory.

assets/agents/deep-research/knowledge/research-style-notes.md

@@ -0,0 +1,49 @@
+# Research style notes
+
+These are general principles the `deep-research` agent should keep in
+mind regardless of topic. Replace this file with your own notes if you
+want to bias retrieval toward your local context.
+
+## What "good research" means here
+
+- **Every factual claim cites a source you actually retrieved.** Never
+  fabricate URLs, page titles, authors, or DOIs.
+- **Primary sources beat aggregators.** Prefer the original paper, the
+  RFC, the standards body, or the manufacturer over a blog summarizing
+  them.
+- **Corroboration matters where stakes are high.** If a single source
+  makes a strong claim, look for a second independent source before
+  taking it as established.
+- **Disagreement is information, not noise.** If two credible sources
+  disagree, report the disagreement and the reasoning on each side.
+- **Old does not mean wrong.** A 2014 RFC is still authoritative if no
+  newer one has obsoleted it; check before assuming a source is stale.
+
+## Source-tier heuristics
+
+The `vet_sources` node uses these rough tiers to weigh credibility.
+The custom tool `classify_source` (see `tools.sh`) implements this
+deterministically by hostname / TLD.
+
+- **HIGH:** government domains (`.gov`, `.mil`), academic institutions
+  (`.edu`, university subdomains), peer-reviewed journals, standards
+  bodies (IETF/RFCs, W3C, ISO, IEEE, NIST), and primary documents from
+  the entities being researched (e.g. a vendor's official spec page).
+- **PREPRINT:** arXiv, bioRxiv, medRxiv, SSRN. Useful but not yet
+  peer-reviewed; treat numeric claims with extra caution.
+- **ORGANIZATION:** established nonprofits, standards-adjacent groups,
+  industry consortia. Reliable for their stated mission but may have a
+  perspective.
+- **UNVERIFIED:** general web pages, blogs, news aggregators, social
+  media. Useful for leads but should not be the only source for a
+  factual claim.
+
+## Common pitfalls to flag in critique
+
+- A claim cited only to a PREPRINT or UNVERIFIED source on a numeric
+  or contested point.
+- A research-plan question that the findings address only obliquely.
+- "Findings" that paraphrase a single source three times rather than
+  triangulating.
+- Citation collisions where two sources are listed but turn out to
+  be the same study reported via different aggregators.

assets/agents/deep-research/scripts/bootstrap_research.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+"""Fan-out source for context loading.
+
+Has no logic of its own. Exists so the static `next: [plan, knowledge_lookup]`
+list on this node fans out into two parallel branches (the LLM planner and
+the RAG knowledge lookup) as a single super-step. The validator requires
+declared parallel-branch script outputs, so we emit an empty JSON object
+explicitly here.
+"""
+import json
+
+
+def main():
+    print(json.dumps({}))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/scripts/combine_findings.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python3
+"""Join the per-question map outputs into a single `findings` string.
+
+The `research_each_question` map writes `question_findings` (an array,
+one entry per sub-question, in input order). Downstream nodes
+(`vet_sources`, `critique`, `synthesize`) read `{{findings}}` as a
+single block, so this script renders the array as a Markdown document
+with one section per question.
+"""
+import json
+import os
+
+
+def load_state():
+    path = os.environ.get("GRAPH_STATE_FILE")
+    if path:
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def main():
+    state = load_state()
+    questions = state.get("questions") or []
+    per_question = state.get("question_findings") or []
+
+    sections = []
+    for idx, q in enumerate(questions):
+        body = per_question[idx] if idx < len(per_question) else ""
+        if isinstance(body, dict) or isinstance(body, list):
+            body = json.dumps(body, indent=2)
+        sections.append(f"## {q}\n\n{body}")
+
+    findings = "\n\n".join(sections) if sections else "No findings gathered."
+    print(json.dumps({"findings": findings}))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/scripts/incorporate_feedback.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+"""Fold a reviewer's free-form feedback back into the research loop.
+
+Runs when the user answers the approval step with their own text
+instead of "accept" or "reject". That text (saved by the approval node
+as `decision`) becomes `research_feedback`, and the graph loops back to
+`research_each_question` for another informed pass (each sub-question is
+re-researched in parallel with the new feedback in context). The
+reflexion counter is reset so the user-driven pass gets a fresh revision
+budget.
+
+Routing (`_next`): always research_each_question.
+"""
+import json
+import os
+
+
+def load_state():
+    path = os.environ.get("GRAPH_STATE_FILE")
+    if path:
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def main():
+    state = load_state()
+    feedback = (state.get("decision") or "").strip()
+    output = {
+        "_next": "research_each_question",
+        "research_attempts": 0,
+        "research_feedback": (
+            "The user reviewed the report and asked for changes. Treat "
+            "this as the top priority for the next pass:\n\n" + feedback
+        ),
+    }
+    print(json.dumps(output))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/scripts/parse_request.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+"""Entry router for deep-research.
+
+Reads the caller's prompt from state. If it contains a usable research
+topic, stores it as `topic` and falls through to the static `next`
+(plan). If the prompt is empty, routes to `ask_topic` so the user can
+supply one interactively.
+
+Routing (`_next`):
+  - prompt present -> (no _next; static next: plan)
+  - prompt empty   -> ask_topic
+"""
+import json
+import os
+
+
+def load_state():
+    path = os.environ.get("GRAPH_STATE_FILE")
+    if path:
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def main():
+    state = load_state()
+    prompt = (state.get("initial_prompt") or "").strip()
+    if prompt:
+        print(json.dumps({"topic": prompt}))
+    else:
+        print(json.dumps({"_next": "ask_topic"}))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/scripts/reflexion_gate.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""Reflexion gate for deep-research.
+
+Runs after `critique` has reviewed the current research findings. If the
+critique's verdict is REVISE and the reflexion budget is not spent,
+loops back to `research` with the critique attached as
+`research_feedback`, so the retry is informed rather than a blind
+re-run. Otherwise it proceeds to `synthesize`.
+
+Routing (`_next`):
+  - verdict PASS                     -> synthesize
+  - verdict REVISE, budget remaining -> research_each_question  (+ research_feedback)
+  - verdict REVISE, budget spent     -> synthesize
+
+Reflexion is a best-effort quality booster, not a hard gate: once the
+budget is spent the workflow proceeds anyway, and the human approval
+step is the final backstop.
+"""
+import json
+import os
+import re
+
+# Automated revision passes allowed. `research` runs at most
+# MAX_REFLEXION_REVISIONS + 1 times per user pass. Bump to allow more.
+MAX_REFLEXION_REVISIONS = 2
+
+
+def load_state():
+    path = os.environ.get("GRAPH_STATE_FILE")
+    if path:
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def as_int(value, default=0):
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def parse_verdict(critique):
+    """Pull PASS/REVISE from the critique's `VERDICT:` line. Defaults to
+    PASS when no verdict line is found, so a malformed critique lets the
+    workflow proceed instead of burning the whole revision budget."""
+    match = re.search(r"VERDICT:\s*([A-Za-z]+)", critique, re.IGNORECASE)
+    if not match:
+        return "PASS"
+    return match.group(1).upper()
+
+
+def main():
+    state = load_state()
+    critique = state.get("critique") or ""
+    verdict = parse_verdict(critique)
+    attempts = as_int(state.get("research_attempts"))
+
+    if verdict == "REVISE" and attempts < MAX_REFLEXION_REVISIONS:
+        feedback = (
+            "A reviewer judged the previous research pass incomplete. "
+            "Address every point in the critique below:\n\n" + critique
+        )
+        output = {
+            "_next": "research_each_question",
+            "research_attempts": attempts + 1,
+            "research_feedback": feedback,
+        }
+    else:
+        output = {"_next": "synthesize"}
+
+    print(json.dumps(output))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/scripts/verify_sources.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+"""Check that the sources cited in the research report are reachable.
+
+Scans the final report for URLs and DOIs, probes each with a HEAD
+request, and writes a `source_check` summary into state so the human
+reviewer sees broken citations at the approval step.
+
+Times out per request so a slow source cannot stall the graph.
+"""
+import json
+import os
+import re
+import urllib.error
+import urllib.request
+
+DOI_RE = re.compile(r"\b(10\.\d{4,9}/[-._;()/:A-Z0-9]+)", re.IGNORECASE)
+URL_RE = re.compile(r"https?://[^\s)\]\}\"'>]+")
+
+
+def load_state():
+    path = os.environ.get("GRAPH_STATE_FILE")
+    if path:
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def reachable(url, timeout=5.0):
+    req = urllib.request.Request(url, method="HEAD")
+    try:
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            return 200 <= resp.status < 400
+    except urllib.error.HTTPError as e:
+        return 200 <= e.code < 400
+    except Exception:
+        return False
+
+
+def main():
+    state = load_state()
+    report = state.get("report") or ""
+
+    urls = sorted({u.rstrip(".,;)") for u in URL_RE.findall(report)})
+    dois = sorted(set(DOI_RE.findall(report)))
+
+    results = []
+    for url in urls:
+        ok = reachable(url)
+        results.append(f"  {'OK' if ok else 'UNREACHABLE'}  {url}")
+    for doi in dois:
+        url = f"https://doi.org/{doi}"
+        if url in urls:
+            continue
+        ok = reachable(url)
+        results.append(f"  {'OK' if ok else 'UNREACHABLE'}  DOI {doi} ({url})")
+
+    if not results:
+        summary = "No web sources were cited in the report."
+    else:
+        summary = (
+            f"Source reachability ({len(results)} checked):\n"
+            + "\n".join(results)
+        )
+
+    print(json.dumps({"source_check": summary}))
+
+
+if __name__ == "__main__":
+    main()

assets/agents/deep-research/tools.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+
+set -e
+
+# @env LLM_OUTPUT=/dev/stdout The output path
+
+# @cmd Classify the credibility tier of a web source from its URL.
+# A deterministic check based on the host and top-level domain. Use it
+# to weigh how much trust to place in a source before relying on it.
+# @option --url!  The full source URL to classify
+classify_source() {
+    # shellcheck disable=SC2154
+    local url="$argc_url"
+    local host="${url#*://}"
+    host="${host%%/*}"
+    host="${host##*@}"
+    host="${host%%:*}"
+    host="$(printf '%s' "$host" | tr '[:upper:]' '[:lower:]')"
+
+    local tier
+    case "$host" in
+        '')
+            tier="UNKNOWN - no host could be parsed from the URL" ;;
+        *.gov | *.gov.* | *.mil)
+            tier="HIGH - government source" ;;
+        *.edu | *.edu.* | *.ac.*)
+            tier="HIGH - academic institution" ;;
+        arxiv.org | *.arxiv.org | biorxiv.org | *.biorxiv.org | medrxiv.org | *.medrxiv.org | ssrn.com | *.ssrn.com)
+            tier="PREPRINT - not yet peer reviewed, corroborate before citing" ;;
+        wikipedia.org | *.wikipedia.org)
+            tier="TERTIARY - encyclopedia, good for orientation not citation" ;;
+        *.org | *.org.*)
+            tier="MEDIUM - organization site, check for institutional bias" ;;
+        *)
+            tier="UNVERIFIED - general web source, corroborate before citing" ;;
+    esac
+
+    printf '%s: %s\n' "${host:-<none>}" "$tier" >> "$LLM_OUTPUT"
+}

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

@@ -2,7 +2,7 @@
 
 An AI agent specialized in exploring codebases, finding patterns, and understanding project structures.
 
-This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent to gather information and context. Sisyphus 
+This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent to gather information and context. Sisyphus
 acts as the coordinator/architect, while Explore handles the research and discovery phase.
 
 It can also be used as a standalone tool for understanding codebases and finding specific information.
@@ -13,3 +13,25 @@ It can also be used as a standalone tool for understanding codebases and finding
 - 📂 File system navigation and content analysis
 - 🧠 Context gathering for complex tasks
 - 🛡️ Read-only operations for safe investigation
+
+## 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](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
+# ...
+
+mcp_servers:
+  - jetbrains # The name of your configured IDE MCP server
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+  - fs_ls.sh
+  - web_search_coyote.sh
+
+# ...
+```

assets/agents/explore/config.yaml

@@ -1,73 +1,115 @@
 name: explore
-description: Fast codebase exploration agent - finds patterns, structures, and relevant files
-version: 1.0.0
-temperature: 0.1
-top_p: 0.95
+description: Fast codebase exploration agent - finds patterns, structures, and relevant files. Designed to be fanned out 2-5 in parallel by orchestrators.
+version: 3.0.0
+
+skills_enabled: true
+enabled_skills:
+  - ai-slop-remover
 
 variables:
   - name: project_dir
     description: Project directory to explore
     default: '.'
 
+mcp_servers:
+  - ddg-search
 global_tools:
   - fs_read.sh
+  - fs_cat.sh
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
 
 instructions: |
   You are a codebase explorer. Your job: Search, find, report. Nothing else.
-  
-  ## Your Mission
-  
-  Given a search task, you:
-  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)
 
-  1. **Find first, read second** - Never read a file without knowing why
-  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
+  ## Step 0: Load your skills
 
-  ## Available Actions
+  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:
+
+  - 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.
+
+  ## You may be one of many parallel explorers
+
+  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.
+
+  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.
+
+  ## Investigation methodology
+
+  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.
+
+  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)
+  - `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:
 
-  - `fs_grep --pattern "struct User" --include "*.rs"` - Find content across files
-  - `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
-  
-  Always end your response with a findings summary:
-  
   ```
   FINDINGS:
-  - [Key finding 1]
-  - [Key finding 2]
-  - Relevant files: [list]
-  
+  - [One-line concrete fact about what you found]
+  - [Another one-line fact]
+  - 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
-  2. **Be focused** - Answer the specific question asked
-  3. **Be concise** - Report findings, not your process
-  4. **Never modify files** - You are read-only
-  5. **Limit reads** - Max 5 file reads per exploration
-  
+
+  1. **Be fast.** Don't read every file, read representative ones.
+  2. **Stay in your slice.** Narrow scope is the contract.
+  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.
+  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:
+  {{__tools__}}
+
 conversation_starters:
   - 'Find how authentication is implemented'
   - 'What patterns are used for API endpoints'

assets/agents/explore/tools.sh

@@ -14,6 +14,21 @@ _project_dir() {
   (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
 }
 
+# Normalize a path to be relative to project root.
+# Strips the project_dir prefix if the LLM passes an absolute path.
+_normalize_path() {
+  local input_path="$1"
+  local project_dir
+  project_dir=$(_project_dir)
+
+  if [[ "${input_path}" == /* ]]; then
+    input_path="${input_path#"${project_dir}"/}"
+  fi
+
+  input_path="${input_path#./}"
+  echo "${input_path}"
+}
+
 # @cmd Get project structure and layout
 get_structure() {
   local project_dir
@@ -45,7 +60,7 @@ search_files() {
   echo "" >> "$LLM_OUTPUT"
   
   local results
-  results=$(search_files "${pattern}" "${project_dir}")
+  results=$(_search_files "${pattern}" "${project_dir}")
   
   if [[ -n "${results}" ]]; then
     echo "${results}" >> "$LLM_OUTPUT"
@@ -78,6 +93,7 @@ search_content() {
     grep -v '/node_modules/' | \
     grep -v '/.git/' | \
     grep -v '/dist/' | \
+    sed "s|^${project_dir}/||" | \
     head -30) || true
   
   if [[ -n "${results}" ]]; then
@@ -91,8 +107,9 @@ search_content() {
 # @option --path! Path to the file (relative to project root)
 # @option --lines Maximum lines to read (default: 200)
 read_file() {
+  local file_path
 	# shellcheck disable=SC2154
-  local file_path="${argc_path}"
+  file_path=$(_normalize_path "${argc_path}")
   local max_lines="${argc_lines:-200}"
   local project_dir
   project_dir=$(_project_dir)
@@ -122,7 +139,8 @@ read_file() {
 # @cmd Find similar files to a given file (for pattern matching)
 # @option --path! Path to the reference file
 find_similar() {
-  local file_path="${argc_path}"
+  local file_path
+  file_path=$(_normalize_path "${argc_path}")
   local project_dir
   project_dir=$(_project_dir)
   
@@ -138,7 +156,7 @@ find_similar() {
     ! -name "$(basename "${file_path}")" \
     ! -name "*test*" \
     ! -name "*spec*" \
-    2>/dev/null | head -5)
+    2>/dev/null | sed "s|^${project_dir}/||" | head -5)
   
   if [[ -n "${results}" ]]; then
     echo "${results}" >> "$LLM_OUTPUT"
@@ -147,7 +165,7 @@ find_similar() {
       ! -name "$(basename "${file_path}")" \
       ! -name "*test*" \
       -not -path '*/target/*' \
-      2>/dev/null | head -5)
+      2>/dev/null | sed "s|^${project_dir}/||" | head -5)
     if [[ -n "${results}" ]]; then
       echo "${results}" >> "$LLM_OUTPUT"
     else

assets/agents/file-reviewer/README.md

@@ -0,0 +1,35 @@
+# File Reviewer
+
+A specialized worker agent that reviews a single file's diff for bugs, style issues, and cross-cutting concerns.
+
+This agent is designed to be spawned by the **[Code Reviewer](../code-reviewer/README.md)** agent. It focuses deeply on 
+one file while communicating with sibling agents to catch issues that span multiple files.
+
+## Features
+
+- 🔍 **Deep Analysis**: Focuses on bugs, logic errors, security issues, and style problems in a single file.
+- 🗣️ **Teammate Communication**: Sends and receives alerts to/from sibling reviewers about interface or dependency 
+  changes.
+- 🎯 **Targeted Reading**: Reads only relevant context around changed lines to stay efficient.
+- 🏷️ **Structured Findings**: Categorizes issues by severity (🔴 Critical, 🟡 Warning, 🟢 Suggestion, 💡 Nitpick).
+
+## 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
+them), and modify the agent definition to look like this:
+
+```yaml
+# ...
+
+mcp_servers:
+  - jetbrains # The name of your configured IDE MCP server
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+
+# ...
+```
+

assets/agents/file-reviewer/config.yaml

@@ -0,0 +1,124 @@
+name: file-reviewer
+description: Reviews a single file's diff for bugs, style issues, and cross-cutting concerns
+version: 2.0.0
+
+skills_enabled: true
+enabled_skills:
+  - code-review
+  - ai-slop-remover
+
+variables:
+  - name: project_dir
+    description: Project directory for context
+    default: '.'
+
+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. Load the review skills (above).
+  2. Analyze the diff applying both skill checklists.
+  3. Read surrounding code for context using the skill's investigation workflow.
+  4. Check your inbox for cross-cutting alerts from sibling reviewers.
+  5. Send alerts to siblings if you spot cross-file issues.
+  6. Return structured findings in the format below.
+
+  ## Input
+
+  You receive:
+  - The file path being reviewed
+  - The git diff for that file
+  - A sibling roster (other file-reviewers and which files they're reviewing)
+
+  ## Cross-Cutting Alerts (Teammate Pattern)
+
+  After analyzing your file, check if changes might affect sibling files:
+  - **Interface changes**: If a function signature changed, alert siblings reviewing callers
+  - **Type changes**: If a type/struct changed, alert siblings reviewing files that use it
+  - **Import changes**: If exports changed, alert siblings reviewing importers
+  - **Config changes**: Alert all siblings if config format changed
+
+  To alert a sibling:
+  ```
+  agent__send_message --to <sibling_agent_id> --message "ALERT: <description of cross-file concern>"
+  ```
+
+  Check your inbox periodically for alerts from siblings:
+  ```
+  agent__check_inbox
+  ```
+
+  If you receive an alert, incorporate it into your findings under a "Cross-File Concerns" section.
+
+  ## File Reading Limits
+
+  The `code-review` skill teaches the investigation workflow. Apply these per-review caps on top:
+  - **Max 5 fs_read calls per review.** Be deliberate about which files you read.
+  - **`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.
+  - **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
+
+  Structure your response EXACTLY as:
+
+  ```
+  ## File: <file_path>
+
+  ### Summary
+  <1-2 sentence summary of the changes>
+
+  ### Findings
+
+  #### <finding_title>
+  - **Severity**: 🔴 CRITICAL | 🟡 WARNING | 🟢 SUGGESTION | 💡 NITPICK
+  - **Lines**: <start_line>-<end_line>
+  - **Description**: <clear explanation of the issue>
+  - **Suggestion**: <how to fix it>
+
+  #### <next_finding_title>
+  ...
+
+  ### Cross-File Concerns
+  <any issues received from siblings or that you alerted siblings about>
+  <"None" if no cross-file concerns>
+
+  REVIEW_COMPLETE
+  ```
+
+  ## Severity Tag Mapping
+
+  Translate the skill's category findings to the output severity:
+  - **🔴 CRITICAL** — Correctness bugs, security vulnerabilities, data loss risks, crashes
+  - **🟡 WARNING** — Logic errors, race conditions, missing error handling, performance issues with user-visible impact
+  - **🟢 SUGGESTION** — Clarity, coupling, naming, footgun mitigations, missing tests for the change
+  - **💡 NITPICK** — Style if no formatter enforces it, minor naming, slop-remover findings on prose-style comments
+
+  ## Rules
+
+  1. **Be specific.** Reference exact line numbers and code.
+  2. **Be actionable.** Every finding must have a suggestion.
+  3. **Never modify files.** You are read-only.
+  4. **Always end with REVIEW_COMPLETE.**
+
+  ## Context
+  - Project: {{project_dir}}
+  - CWD: {{__cwd__}}
+
+  ## Available Tools:
+  {{__tools__}}

assets/agents/file-reviewer/tools.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+# shellcheck disable=SC1090
+source "$LLM_PROMPT_UTILS_FILE"
+source "$LLM_ROOT_DIR/agents/.shared/utils.sh"
+
+# @env LLM_OUTPUT=/dev/stdout
+# @env LLM_AGENT_VAR_PROJECT_DIR=.
+# @describe File reviewer tools for single-file code review
+
+_project_dir() {
+  local dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
+  (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
+}
+
+# @cmd Get project structure to understand codebase layout
+get_structure() {
+  local project_dir
+  project_dir=$(_project_dir)
+
+  info "Project structure:" >> "$LLM_OUTPUT"
+  echo "" >> "$LLM_OUTPUT"
+
+  local project_info
+  project_info=$(detect_project "${project_dir}")
+
+  {
+    echo "Type: $(echo "${project_info}" | jq -r '.type')"
+    echo ""
+    get_tree "${project_dir}" 2
+  } >> "$LLM_OUTPUT"
+}

assets/agents/jira-helper/README.md

@@ -1,14 +0,0 @@
-# Jira AI Agent
-
-## Overview
-
-The Jira AI Agent is designed to assist with managing tasks within Jira projects, providing capabilities such as 
-creating, searching, updating, assigning, linking, and commenting on issues. Its primary purpose is to help software 
-engineers seamlessly integrate Jira into their workflows through an AI-driven interface.
-
-## Configuration
-This agent uses the official [Atlassian MCP Server](https://github.com/atlassian/atlassian-mcp-server). To use it, 
-ensure you have Node.js v18+ installed to run the local MCP proxy (`mcp-remote`).
-
-The server uses OAuth 2.0 so it will automatically open your browser for you to sign in to your account. No manual 
-configuration is necessary!

assets/agents/jira-helper/config.yaml

@@ -1,37 +0,0 @@
-name: Jira Agent
-description: An AI agent that can assist with Jira tasks such as creating issues, searching for issues, and updating issues.
-version: 0.1.0
-agent_session: temp
-mcp_servers:
-  - atlassian
-instructions: |
-  You are a AI agent designed to assist with managing Jira tasks and helping software engineers utilize and integrate 
-  Jira into their workflows. You can create, search, update, assign, link, and comment on issues in Jira.
-  
-  ## Create Issue (MANDATORY when creating a issue)
-  When a user prompts you to create a Jira issue:
-  1. Prompt the user for what Jira project they want the ticket created in
-  2. If the ticket type requires a parent issue:
-    a. Query Jira for potentially relevant parents
-    b. Prompt user for which parent to use, displaying the suggested list of parent issues
-  3. Create the issue with the following format:
-     ```markdown
-      **Description:**
-        This section gives context and details about the issue.
-      **User Acceptance Criteria:**
-        # This section provides bullet points that function like a checklist of all the things that must be completed in 
-        # order for the issue to be considered done.
-        * Example criteria one
-        * Example criteria two
-     ```
-  4. Ask the user if the issue should be assigned to them
-    a. If yes, then assign the user to the newly created issue
-
-
-  Available tools:
-  {{__tools__}}
-conversation_starters:
-  - What are the latest issues in my Jira project?
-  - Can you create a new Jira issue for me?
-  - What are my open Jira issues?
-  - Can you search for issues with the label "bug" in my Jira project?

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

@@ -2,7 +2,7 @@
 
 An AI agent specialized in high-level architecture, complex debugging, and design decisions.
 
-This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent when deep reasoning, architectural advice, 
+This agent is designed to be delegated to by the **[Sisyphus](../sisyphus/README.md)** agent when deep reasoning, architectural advice,
 or complex problem-solving is required. Sisyphus acts as the coordinator, while Oracle provides the expert analysis and
 recommendations.
 
@@ -15,3 +15,25 @@ It can also be used as a standalone tool for design reviews and solving difficul
 - ⚖️ Tradeoff analysis and technology selection
 - 📝 Code review and best practices advice
 - 🧠 Deep reasoning for ambiguous problems
+
+## 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](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
+# ...
+
+mcp_servers:
+  - jetbrains # The name of your configured IDE MCP server
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+  - fs_ls.sh
+  - web_search_coyote.sh
+
+# ...
+```

assets/agents/oracle/config.yaml

@@ -1,81 +1,111 @@
 name: oracle
-description: High-IQ advisor for architecture, debugging, and complex decisions
-version: 1.0.0
-temperature: 0.2
-top_p: 0.95
+description: High-IQ advisor for architecture, debugging, and complex decisions. Blocking by design - the orchestrator is waiting on you.
+version: 2.0.0
+
+skills_enabled: true
+enabled_skills:
+  - code-review
+  - ai-slop-remover
 
 variables:
   - name: project_dir
     description: Project directory for context
     default: '.'
 
+mcp_servers:
+  - ddg-search
 global_tools:
   - fs_read.sh
+  - fs_cat.sh
   - fs_grep.sh
   - fs_glob.sh
   - fs_ls.sh
-  - execute_command.sh
 
 instructions: |
-  You are Oracle - a senior architect and debugger consulted for complex decisions.
-  
-  ## Your Role
-  
-  You are READ-ONLY. You analyze, advise, and recommend. You do NOT implement.
-  
-  ## When You're Consulted
-  
-  1. **Architecture Decisions**: Multi-system tradeoffs, design patterns, technology choices
-  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)
+  You are Oracle - a senior architect and debugger consulted for the hard, multi-dimensional decisions a coordinator cannot make alone.
 
-  1. **Use grep to find relevant code** - `fs_grep --pattern "auth" --include "*.rs"` finds where things are
-  2. **Read only what you need** - `fs_read --path "src/main.rs" --offset 50 --limit 30` reads lines 50-79
-  3. **Never read entire large files** - If 500+ lines, grep first, then read the relevant section
-  4. **Use glob to discover files** - `fs_glob --pattern "*.rs" --path src/`
+  ## Your role
 
-  ## Your Process
+  You are READ-ONLY. You analyze, advise, recommend. You do NOT implement. Implementation is for the coder agent.
+
+  ## You are blocking by design
+
+  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.
+
+  Therefore:
+
+  - **Be thorough, not just fast.** A quick wrong answer wastes more downstream time than a careful right answer.
+  - **Read the relevant context** before advising. Don't guess from the prompt alone.
+  - **Consider tradeoffs explicitly.** There are rarely perfect solutions; surface the alternatives.
+  - **Justify your recommendation.** The orchestrator (and ultimately the user) needs to understand WHY, not just WHAT.
+
+  ## When you're consulted
+
+  1. **Architecture decisions** — multi-system tradeoffs, design patterns, technology choices.
+  2. **Complex debugging** — after 2+ failed fix attempts, or when the symptom doesn't match the obvious cause.
+  3. **Code review** — evaluating proposed designs or implementations.
+  4. **Risk assessment** — security, performance, reliability concerns.
+  5. **Multi-component questions** — anything spanning 3+ files or modules.
+
+  ## Skills available
+
+  Two skills are available to you. Load them 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).
+
+  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
 
-  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
-  4. **Justify**: Explain your reasoning
-  
-  ## 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]
-  
-  ## Risks/Considerations
-  [What to watch out for]
-  
+  [Why this is the right approach. What you considered and rejected, and why.]
+
+  ## Risks / Considerations
+  [What to watch out for during implementation. Known footguns. Edge cases.]
+
   ORACLE_COMPLETE
   ```
-  
+
   ## Rules
-  
-  1. **Never modify files** - You advise, others implement
-  2. **Be thorough** - Read all relevant context before advising
-  3. **Be specific** - General advice isn't helpful
-  4. **Consider tradeoffs** - There are rarely perfect solutions
-  5. **Stay focused** - Answer the specific question asked
-  
+
+  1. **Never modify files** — you advise, others implement.
+  2. **Be thorough** — read all relevant context before advising. Speed is not the goal; correctness is.
+  3. **Be specific** — general advice ("use SOLID principles") isn't actionable.
+  4. **Consider tradeoffs** — surface the alternatives you rejected and why.
+  5. **Stay focused** — answer the specific question asked, but flag adjacent risks you notice.
+
   ## Context
   - Project: {{project_dir}}
   - CWD: {{__cwd__}}
 
+  ## Available tools:
+  {{__tools__}}
+
 conversation_starters:
   - 'Review this architecture design'
   - 'Help debug this complex issue'

assets/agents/oracle/tools.sh

@@ -14,21 +14,38 @@ _project_dir() {
   (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
 }
 
+# Normalize a path to be relative to project root.
+# Strips the project_dir prefix if the LLM passes an absolute path.
+_normalize_path() {
+  local input_path="$1"
+  local project_dir
+  project_dir=$(_project_dir)
+
+  if [[ "${input_path}" == /* ]]; then
+    input_path="${input_path#"${project_dir}"/}"
+  fi
+
+  input_path="${input_path#./}"
+  echo "${input_path}"
+}
+
 # @cmd Read a file for analysis
 # @option --path! Path to the file (relative to project root)
 read_file() {
   local project_dir
   project_dir=$(_project_dir)
+  local file_path
   # shellcheck disable=SC2154
-  local full_path="${project_dir}/${argc_path}"
+  file_path=$(_normalize_path "${argc_path}")
+  local full_path="${project_dir}/${file_path}"
   
   if [[ ! -f "${full_path}" ]]; then
-    error "File not found: ${argc_path}" >> "$LLM_OUTPUT"
+    error "File not found: ${file_path}" >> "$LLM_OUTPUT"
     return 1
   fi
 
   {
-  	info "Reading: ${argc_path}"
+  	info "Reading: ${file_path}"
   	echo ""
   	cat "${full_path}"
   } >> "$LLM_OUTPUT"
@@ -80,6 +97,7 @@ search_code() {
     grep -v '/target/' | \
     grep -v '/node_modules/' | \
     grep -v '/.git/' | \
+    sed "s|^${project_dir}/||" | \
     head -30) || true
   
   if [[ -n "${results}" ]]; then
@@ -113,7 +131,8 @@ analyze_with_command() {
 # @cmd List directory contents
 # @option --path Path to list (default: project root)
 list_directory() {
-  local dir_path="${argc_path:-.}"
+  local dir_path
+  dir_path=$(_normalize_path "${argc_path:-.}")
   local project_dir
   project_dir=$(_project_dir)
   local full_path="${project_dir}/${dir_path}"

assets/agents/report-writer/README.md

@@ -0,0 +1,46 @@
+# report-writer
+
+A tiny, focused sub-agent that turns a set of research findings into a
+single coherent final report. Reads only what it is given — does not
+do independent research, does not access the web, does not invent
+facts. It exists as a focused tool for orchestrating agents to
+delegate the writing phase to.
+
+## Why a separate agent?
+
+This is an example of the **agent-as-tool** pattern in graph agents.
+The `deep-research` graph agent's `synthesize` node is an `agent` node
+that spawns this one (see `assets/agents/deep-research/graph.yaml`).
+Separating the role has two practical benefits:
+
+- The orchestrating agent can use a cheap model (or a high-temperature
+  exploratory one) for the research phase, while letting the writing
+  phase use a different (typically lower-temperature, possibly larger)
+  model dedicated to coherent prose.
+- The writing prompt is owned by this agent's `config.yaml` rather
+  than buried inside another agent's graph. You can polish it
+  independently without touching the research flow.
+
+## Standalone use
+
+You can also use this agent directly if you have a set of findings you
+want polished:
+
+```sh
+coyote -a report-writer "Topic: X. Findings: <paste findings here>"
+```
+
+It will produce a single Markdown report following the rules in its
+system prompt: executive summary at the top, grouped sections by
+related sub-questions, every inline citation preserved verbatim, and a
+final "Open questions / disagreements" section.
+
+## What it will NOT do
+
+- Search the web, fetch URLs, query an MCP server, or use any tool.
+  It has no tools configured.
+- Invent facts beyond what is in the findings you give it.
+- Strip or rewrite citations.
+
+These constraints are the point of the agent existing: a writer that
+the orchestrator can trust to stay in its lane.

assets/agents/report-writer/config.yaml

@@ -0,0 +1,33 @@
+name: report-writer
+description: Polishes research findings into a clear, citation-preserving final report
+version: 1.0.0
+
+instructions: |
+  You are a technical writer. You will be given:
+    - a research topic
+    - a set of findings, organized per sub-question, with inline
+      citations next to each claim
+    - a source-credibility assessment of the cited sources
+
+  Your job is to produce a single, well-organized final report:
+
+  Rules:
+    - Use ONLY the findings provided. Do not introduce facts from
+      your own memory. Do not speculate beyond what the findings
+      support.
+    - Preserve every inline citation. If a sentence in the findings
+      had a URL or DOI, the equivalent sentence in your report must
+      keep the same citation.
+    - Lead with a 2-3 sentence executive summary at the top.
+    - Organize the body so that related sub-questions are grouped,
+      not strictly one section per question. The findings are raw
+      material; the report should read as a single coherent answer
+      to the original topic.
+    - End with a short "Open questions / disagreements" section
+      naming anything the findings flagged as unresolved or
+      contested.
+
+  Output plain Markdown. No metadata, no JSON wrapper.
+
+conversation_starters:
+  - "Polish these findings into a cited report"

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._
@@ -16,3 +16,25 @@ 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.
+
+## 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 coyote config (see the
+[MCP Server docs](https://github.com/Dark-Alex-17/loki/wiki/MCP-Servers)) and reference it in this agent's `mcp_servers:` list:
+
+```yaml
+# ...
+
+mcp_servers:
+  - your-ide-mcp-server
+
+global_tools:
+  - fs_read.sh
+  - fs_grep.sh
+  - fs_glob.sh
+  - fs_ls.sh
+  - web_search_coyote.sh
+  - execute_command.sh
+
+# ...
+```

assets/agents/sisyphus/config.yaml

@@ -1,14 +1,29 @@
 name: sisyphus
-description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos
-version: 1.0.0
-temperature: 0.1
-top_p: 0.95
+description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos, enforces OMO-grade verification discipline
+version: 3.0.0
 
-agent_session: sisyphus
+agent_session: temp
 auto_continue: true
 max_auto_continues: 25
 inject_todo_instructions: true
 
+can_spawn_agents: true
+max_concurrent_agents: 4
+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
+
 variables:
   - name: project_dir
     description: Project directory to work in
@@ -17,171 +32,352 @@ variables:
     description: Auto-confirm command execution
     default: '1'
 
+mcp_servers:
+  - ddg-search
 global_tools:
   - fs_read.sh
   - 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 |
-  |------|--------|--------|
-  | Trivial | Single file, known location, typo fix | Do it yourself with tools |
-  | Exploration | "Find X", "Where is Y", "List all Z" | Delegate to `explore` agent |
-  | Implementation | "Add feature", "Fix bug", "Write code" | Delegate to `coder` agent |
-  | Architecture/Design | See oracle triggers below | Delegate to `oracle` agent |
-  | Ambiguous | Unclear scope, multiple interpretations | ASK the user |
+  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.
 
-  ### Oracle Triggers (MUST delegate to 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."
 
-  Delegate to `oracle` ANY time the user asks about:
-  - **"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"
+     The verbalization anchors routing and makes reasoning transparent. It does NOT commit you to implementation — only the user's explicit request does that.
 
-  **CRITICAL**: Do NOT answer architecture/design questions yourself. You are a coordinator.
-  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.
+  2. **Classify** (after verbalizing):
 
-  ## Context System (CRITICAL for multi-step tasks)
+     | 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` |
 
-  Context is shared between you and your subagents. This lets subagents know what you've learned.
+  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.
 
-  **At the START of a multi-step task:**
-  ```
-  start_task --goal "Description of overall task"
-  ```
+  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**.
 
-  **During work** (automatically captured from delegations, or manually):
-  ```
-  record_finding --source "manual" --finding "Important discovery"
-  ```
+  ## Oracle Triggers (MUST spawn oracle when you see these)
 
-  **To see accumulated context:**
-  ```
-  show_context
-  ```
+  - "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"
 
-  **When task is COMPLETE:**
-  ```
-  end_task
-  ```
+  **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.
 
-  When you delegate, subagents automatically receive all accumulated context.
+  ## Phase 1 - Skills Discovery (FIRST TIME per session, or when phase changes)
 
-  ## Todo System (MANDATORY for multi-step tasks)
+  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.
 
-  For ANY task with 2+ steps:
-  1. Call `start_task` with the goal (initializes context)
-  2. Call `todo__init` with the goal
-  3. Call `todo__add` for each step BEFORE starting
-  4. Work through steps, calling `todo__done` IMMEDIATELY after each
-  5. The system auto-continues until all todos are done
-  6. Call `end_task` when complete (clears context)
+  **When to load which skill:**
 
-  ## Delegation Pattern
+  | 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` |
 
-  When delegating, use `delegate_to_agent` with:
-  - agent: explore | coder | oracle
-  - task: Specific, atomic goal
-  - context: Additional context beyond what's in the shared context file
+  Load skills BEFORE the phase, not after. Unload when the phase ends if context is getting heavy. `skill__unload` keeps the context lean.
 
-  The shared context (from `start_task` and prior delegations) is automatically injected.
+  ## Phase 2 - Codebase Assessment (Open-ended tasks only)
 
-  **CRITICAL**: After delegation, VERIFY the result before marking the todo done.
+  For "improve X" / "refactor Y" / "clean up Z" type requests, quick-assess the codebase state BEFORE following patterns:
 
-  ## Agent Specializations
+  - **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 |
-  | coder | Write/edit files, implement features | Creates/modifies files, runs builds |
-  | oracle | Architecture decisions, complex debugging | Advisory, high-quality reasoning |
+  | `explore` | Find patterns in THIS codebase, understand local code | Read-only, returns findings, fan out 2-5 in parallel |
+  | `librarian` | Find official docs, OSS examples, web best practices for EXTERNAL libraries | Read-only, returns citation-backed findings, fan out 1-3 in parallel |
+  | `coder` | Write/edit files, implement features | Graph agent: plan → approval → implement → verify build+tests → self_review → bounded fix-loop |
+  | `oracle` | Architecture, complex debugging, review | Advisory, blocking — never answer the user before collecting Oracle results |
 
-  ## Workflow Examples
+  ### When to fire `librarian` (external grep) vs `explore` (internal grep)
 
-  ### Example 1: Implementation task (explore -> coder)
+  - User mentions an unfamiliar npm/pip/cargo/crate package → fire `librarian` for official docs
+  - 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
 
-  User: "Add a new API endpoint for user profiles"
+  ### 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:
 
   ```
-  1. start_task --goal "Add user profiles API endpoint"
-  2. todo__init --goal "Add user profiles API endpoint"
-  3. todo__add --task "Explore existing API patterns"
-  4. todo__add --task "Implement profile endpoint"
-  5. todo__add --task "Verify with build/test"
-  6. delegate_to_agent --agent explore --task "Find existing API endpoint patterns and structures"
-  7. todo__done --id 1
-  8. delegate_to_agent --agent coder --task "Create user profiles endpoint following existing patterns"
-  9. todo__done --id 2
-  10. run_build
-  11. run_tests
-  12. todo__done --id 3
-  13. end_task
+  ## TASK
+  [One atomic goal: what to build/modify and where]
+
+  ## EXPECTED OUTCOME
+  [Concrete deliverables. "Done when ..."]
+
+  ## REQUIRED TOOLS
+  [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:
+  [5-20 lines pasted from explore results]
+  </code>
+
+  Skill nudge: load `frontend-ui-ux` before touching components.
   ```
 
-  ### Example 2: Architecture/design question (explore -> oracle)
+  **Paste actual code snippets, not just file paths.** "Follow existing patterns" with no example wastes coder's tokens on re-exploration you already did.
 
-  User: "How should I structure the authentication for this app?"
+  ### Session continuity (NON-NEGOTIABLE)
+
+  Every `agent__spawn` result includes a session_id. Store it.
+
+  - 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. start_task --goal "Get architecture advice for authentication"
-  2. todo__init --goal "Get architecture advice for authentication"
-  3. todo__add --task "Explore current auth-related code"
-  4. todo__add --task "Consult oracle for architecture recommendation"
-  5. delegate_to_agent --agent explore --task "Find any existing auth code, middleware, user models, and session handling"
-  6. todo__done --id 1
-  7. delegate_to_agent --agent oracle --task "Recommend authentication architecture" --context "User wants auth advice. Explore found: [summarize findings]. Evaluate approaches and recommend the best one with justification."
-  8. todo__done --id 2
-  9. end_task
+  agent__spawn --agent code-reviewer --prompt "Review the changes from the recent coder run(s) for this task.
+
+  Original request: <one-line summary of what the user asked for>
+  Scope: <which directories or files the changes are expected to touch>
+
+  Coder summaries:
+  - <coder 1 session_id>: <plan_summary from CODER_COMPLETE>
+  - <coder 2 session_id>: <plan_summary if multiple coders ran>
+
+  Run `get_diff` against the staged or recent changes, fan out file-reviewers per changed file as usual, and synthesize."
   ```
 
-  ### Example 3: Vague/open-ended question (oracle directly)
+  ### Handling code-reviewer findings
 
-  User: "What do you think of this codebase structure?"
+  - **🔴 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.
 
-  ```
-  1. delegate_to_agent --agent oracle --task "Review the project structure and provide recommendations for improvement"
-     # Oracle will read files and analyze on its own
-  ```
+  ### When NOT to re-spawn code-reviewer
 
-  ## Rules
+  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. **Always start_task first** - Initialize context before multi-step work
-  2. **Always classify before acting** - Don't jump into implementation
-  3. **Create todos for multi-step tasks** - Track your progress
-  4. **Delegate specialized work** - You're a coordinator, not an implementer
-  5. **Verify after delegation** - Don't trust blindly
-  6. **Mark todos done immediately** - Don't batch completions
-  7. **Ask when ambiguous** - One clarifying question is better than wrong work
-  8. **Always end_task** - Clean up context when done
+  ## File Operations (Direct Edits)
 
-  ## When to Do It Yourself
+  When you write or modify files yourself (rather than delegating to coder):
 
-  - Single-file reads/writes
-  - Simple command execution
-  - Trivial changes (typos, renames)
-  - Quick file searches
+  - **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.
+  - **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.
+  - **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
 
-  ## When to NEVER Do It Yourself
+    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.
 
-  - 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
+  - **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.
+  - **For listing/searching**, prefer `fs_ls`, `fs_glob`, `fs_grep` over shell equivalents (`ls`, `find`, `grep`).
+
+  `execute_command` is for: git operations, build/test commands, package management, runtime inspection (`ps`, `df`, etc.) — anything where the shell IS the right interface.
+
+  ## Phase 7 - Failure Recovery
+
+  ### 3-strike rule
+
+  After 3 consecutive failed fix attempts on the same problem:
+
+  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.
+
+  ## 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'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:
+
+  - `CODER_COMPLETE` — build + tests green. Continue with 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_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>`).
+
+  ## Escalation Handling
+
+  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.
+
+  ## 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/sisyphus/tools.sh

@@ -7,126 +7,18 @@ export AUTO_CONFIRM=true
 
 # @env LLM_OUTPUT=/dev/stdout
 # @env LLM_AGENT_VAR_PROJECT_DIR=.
-# @describe Sisyphus orchestrator tools for delegating to specialized agents
+# @describe Sisyphus orchestrator tools (project info, build, test)
 
 _project_dir() {
   local dir="${LLM_AGENT_VAR_PROJECT_DIR:-.}"
   (cd "${dir}" 2>/dev/null && pwd) || echo "${dir}"
 }
 
-# @cmd Initialize context for a new task (call at the start of multi-step work)
-# @option --goal! Description of the overall task/goal
-start_task() {
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  export LLM_AGENT_VAR_PROJECT_DIR="${project_dir}"
-  # shellcheck disable=SC2154
-  init_context "${argc_goal}"
-
-  cat <<-EOF >> "$LLM_OUTPUT"
-  	$(green "Context initialized for task: ${argc_goal}")
-  	Context file: ${project_dir}/.loki-context
-	EOF
-}
-
-# @cmd Add a finding to the shared context (useful for recording discoveries)
-# @option --source! Source of the finding (e.g., "manual", "explore", "coder")
-# @option --finding! The finding to record
-record_finding() {
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  export LLM_AGENT_VAR_PROJECT_DIR="${project_dir}"
-  # shellcheck disable=SC2154
-  append_context "${argc_source}" "${argc_finding}"
-  
-  green "Recorded finding from ${argc_source}" >> "$LLM_OUTPUT"
-}
-
-# @cmd Show current accumulated context
-show_context() {
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  export LLM_AGENT_VAR_PROJECT_DIR="${project_dir}"
-  local context
-  context=$(read_context)
-  
-  if [[ -n "${context}" ]]; then
-    cat <<-EOF >> "$LLM_OUTPUT"
-    	$(info "Current Context:")
-
-    	${context}
-		EOF
-  else
-    warn "No context file found. Use start_task to initialize." >> "$LLM_OUTPUT"
-  fi
-}
-
-# @cmd Clear the context file (call when task is complete)
-end_task() {
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  export LLM_AGENT_VAR_PROJECT_DIR="${project_dir}"
-  clear_context
-  
-  green "Context cleared. Task complete." >> "$LLM_OUTPUT"
-}
-
-# @cmd Delegate a task to a specialized agent
-# @option --agent! Agent to delegate to: explore, coder, or oracle
-# @option --task! Specific task description for the agent
-# @option --context Additional context (file paths, patterns, constraints)
-delegate_to_agent() {
-  local extra_context="${argc_context:-}"
-  local project_dir
-  project_dir=$(_project_dir)
-
-  # shellcheck disable=SC2154
-  if [[ ! "${argc_agent}" =~ ^(explore|coder|oracle)$ ]]; then
-    error "Invalid agent: ${argc_agent}. Must be explore, coder, or oracle" >> "$LLM_OUTPUT"
-    return 1
-  fi
-  
-  export LLM_AGENT_VAR_PROJECT_DIR="${project_dir}"
-  
-  info "Delegating to ${argc_agent} agent..." >> "$LLM_OUTPUT"
-  echo "" >> "$LLM_OUTPUT"
-
-	# shellcheck disable=SC2154
-  local prompt="${argc_task}"
-  if [[ -n "${extra_context}" ]]; then
-    prompt="$(printf "%s\n\nAdditional Context:\n%s\n" "${argc_task}" "${extra_context}")"
-  fi
-
-  cat <<-EOF >> "$LLM_OUTPUT"
-  $(cyan "------------------------------------------")
-  DELEGATING TO: ${argc_agent}
-  TASK: ${argc_task}
-  $(cyan "------------------------------------------")
-
-	EOF
-  
-  local output
-  output=$(invoke_agent_with_summary "${argc_agent}" "${prompt}" \
-    --agent-variable project_dir "${project_dir}" 2>&1) || true
-
-  cat <<-EOF >> "$LLM_OUTPUT"
-  ${output}
-
-  $(cyan "------------------------------------------")
-  DELEGATION COMPLETE: ${argc_agent}
-  $(cyan "------------------------------------------")
-	EOF
-}
-
 # @cmd Get project information and structure
 get_project_info() {
   local project_dir
   project_dir=$(_project_dir)
-  
+
   info "Project: ${project_dir}" >> "$LLM_OUTPUT"
   echo "" >> "$LLM_OUTPUT"
 
@@ -147,17 +39,17 @@ get_project_info() {
 run_build() {
   local project_dir
   project_dir=$(_project_dir)
-  
+
   local project_info
   project_info=$(detect_project "${project_dir}")
   local build_cmd
   build_cmd=$(echo "${project_info}" | jq -r '.build')
-  
+
   if [[ -z "${build_cmd}" ]] || [[ "${build_cmd}" == "null" ]]; then
     warn "No build command detected for this project" >> "$LLM_OUTPUT"
     return 0
   fi
-  
+
   info "Running: ${build_cmd}" >> "$LLM_OUTPUT"
   echo "" >> "$LLM_OUTPUT"
 
@@ -177,17 +69,17 @@ run_build() {
 run_tests() {
   local project_dir
   project_dir=$(_project_dir)
-  
+
   local project_info
   project_info=$(detect_project "${project_dir}")
   local test_cmd
   test_cmd=$(echo "${project_info}" | jq -r '.test')
-  
+
   if [[ -z "${test_cmd}" ]] || [[ "${test_cmd}" == "null" ]]; then
     warn "No test command detected for this project" >> "$LLM_OUTPUT"
     return 0
   fi
-  
+
   info "Running: ${test_cmd}" >> "$LLM_OUTPUT"
   echo "" >> "$LLM_OUTPUT"
 
@@ -203,53 +95,3 @@ run_tests() {
   fi
 }
 
-# @cmd Quick file search in the project
-# @option --pattern! File name pattern to search for (e.g., "*.rs", "config*")
-search_files() {
-	# shellcheck disable=SC2154
-  local pattern="${argc_pattern}"
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  info "Searching for: ${pattern}" >> "$LLM_OUTPUT"
-  echo "" >> "$LLM_OUTPUT"
-
-  local results
-  results=$(search_files "${pattern}" "${project_dir}")
-  
-  if [[ -n "${results}" ]]; then
-    echo "${results}" >> "$LLM_OUTPUT"
-  else
-    warn "No files found matching: ${pattern}" >> "$LLM_OUTPUT"
-  fi
-}
-
-# @cmd Search for content in files
-# @option --pattern! Text pattern to search for
-# @option --file-type File extension to search in (e.g., "rs", "py")
-search_content() {
-  local pattern="${argc_pattern}"
-  local file_type="${argc_file_type:-}"
-  local project_dir
-  project_dir=$(_project_dir)
-  
-  info "Searching for: ${pattern}" >> "$LLM_OUTPUT"
-  echo "" >> "$LLM_OUTPUT"
-  
-  local grep_args="-rn"
-  if [[ -n "${file_type}" ]]; then
-    grep_args="${grep_args} --include=*.${file_type}"
-  fi
-  
-  local results
-  # shellcheck disable=SC2086
-  results=$(grep ${grep_args} "${pattern}" "${project_dir}" 2>/dev/null | \
-    grep -v '/target/' | grep -v '/node_modules/' | grep -v '/.git/' | \
-    head -30) || true
-  
-  if [[ -n "${results}" ]]; then
-    echo "${results}" >> "$LLM_OUTPUT"
-  else
-    warn "No matches found for: ${pattern}" >> "$LLM_OUTPUT"
-  fi
-}

assets/functions/mcp.json

@@ -1,26 +1,23 @@
 {
   "mcpServers": {
     "github": {
-      "command": "docker",
-      "args": [
-        "run",
-        "-i",
-        "--rm",
-        "-e",
-        "GITHUB_PERSONAL_ACCESS_TOKEN",
-        "ghcr.io/github/github-mcp-server"
-      ],
-      "env": {
-        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN"
-      }
+      "type": "http",
+      "url": "https://api.githubcopilot.com/mcp"
     },
     "atlassian": {
+      "type": "stdio",
       "command": "npx",
-      "args": ["-y", "mcp-remote@0.1.13", "https://mcp.atlassian.com/v1/sse"]
+      "args": ["-y", "mcp-remote@latest", "https://mcp.atlassian.com/v1/mcp"]
     },
     "docker": {
+      "type": "stdio",
       "command": "uvx",
       "args": ["mcp-server-docker"]
+    },
+    "ddg-search": {
+      "type": "stdio",
+      "command": "uvx",
+      "args": ["duckduckgo-mcp-server"]
     }
   }
 }

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)
@@ -50,7 +50,13 @@ def parse_raw_data(data):
 
 def parse_argv():
     agent_func = sys.argv[1]
-    agent_data = sys.argv[2]
+
+    tool_data_file = os.environ.get("LLM_TOOL_DATA_FILE")
+    if tool_data_file and os.path.isfile(tool_data_file):
+        with open(tool_data_file, "r", encoding="utf-8") as f:
+            agent_data = f.read()
+    else:
+        agent_data = sys.argv[2]
 
     if (not agent_data) or (not agent_func):
         print("Usage: ./{agent_name}.py <agent-func> <agent-data>", file=sys.stderr)
@@ -59,13 +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

@@ -14,7 +14,11 @@ main() {
 
 parse_argv() {
 		agent_func="$1"
-		agent_data="$2"
+    if [[ -n "$LLM_TOOL_DATA_FILE" ]] && [[ -f "$LLM_TOOL_DATA_FILE" ]]; then
+      	agent_data="$(cat "$LLM_TOOL_DATA_FILE")"
+    else
+				agent_data="$2"
+    fi
     if [[ -z "$agent_data" ]] || [[ -z "$agent_func" ]]; then
         die "usage: ./{agent_name}.sh <agent-func> <agent-data>"
     fi
@@ -28,6 +32,7 @@ setup_env() {
     export LLM_AGENT_ROOT_DIR="$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() {
@@ -57,7 +62,6 @@ run() {
     if [[ "$OS" == "Windows_NT" ]]; then
         set -o igncr
         tools_path="$(cygpath -w "$tools_path")"
-        tool_data="$(echo "$tool_data" | sed 's/\\/\\\\/g')"
     fi
 
     jq_script="$(cat <<-'EOF'
@@ -70,11 +74,11 @@ def to_args:
     to_entries | .[] |
     (.key | split("_") | join("-")) as $key |
     if .value | type == "array" then
-        .value | .[] | "--\($key) \(. | escape_shell_word)"
+        .value | .[] | "--\($key)=\(. | escape_shell_word)"
     elif .value | type == "boolean" then
         if .value then "--\($key)" else "" end
     else
-        "--\($key) \(.value | escape_shell_word)"
+        "--\($key)=\(.value | escape_shell_word)"
     end;
 [ to_args ] | join(" ")
 EOF

assets/functions/scripts/run-agent.ts

@@ -0,0 +1,190 @@
+#!/usr/bin/env tsx
+
+// Usage: ./{agent_name}.ts <agent-func> <agent-data>
+
+import { readFileSync, writeFileSync, existsSync } from "fs";
+import { join } from "path";
+import { pathToFileURL } from "url";
+
+async function main(): Promise<void> {
+  const { agentFunc, rawData } = parseArgv();
+  const agentData = parseRawData(rawData);
+
+  const configDir = "{config_dir}";
+  setupEnv(configDir, agentFunc, rawData);
+
+  const agentToolsPath = join(configDir, "agents", "{agent_name}", "tools.ts");
+  await run(agentToolsPath, agentFunc, agentData);
+}
+
+function parseRawData(data: string): Record<string, unknown> {
+  if (!data) {
+    throw new Error("No JSON data");
+  }
+
+  try {
+    return JSON.parse(data);
+  } catch {
+    throw new Error("Invalid JSON data");
+  }
+}
+
+function parseArgv(): { agentFunc: string; rawData: string } {
+  const agentFunc = process.argv[2];
+
+  const toolDataFile = process.env["LLM_TOOL_DATA_FILE"];
+  let agentData: string;
+  if (toolDataFile && existsSync(toolDataFile)) {
+    agentData = readFileSync(toolDataFile, "utf-8");
+  } else {
+    agentData = process.argv[3];
+  }
+
+  if (!agentFunc || !agentData) {
+    process.stderr.write("Usage: ./{agent_name}.ts <agent-func> <agent-data>\n");
+    process.exit(1);
+  }
+
+  return { agentFunc, rawData: agentData };
+}
+
+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 {
+  let lines: string[];
+  try {
+    lines = readFileSync(filePath, "utf-8").split("\n");
+  } catch {
+    return;
+  }
+
+  for (const raw of lines) {
+    const line = raw.trim();
+    if (line.startsWith("#") || !line) {
+      continue;
+    }
+
+    const eqIdx = line.indexOf("=");
+    if (eqIdx === -1) {
+      continue;
+    }
+
+    const key = line.slice(0, eqIdx).trim();
+    if (key in process.env) {
+      continue;
+    }
+
+    let value = line.slice(eqIdx + 1).trim();
+    if (
+      (value.startsWith('"') && value.endsWith('"')) ||
+      (value.startsWith("'") && value.endsWith("'"))
+    ) {
+      value = value.slice(1, -1);
+    }
+    process.env[key] = value;
+  }
+}
+
+function extractParamNames(fn: Function): string[] {
+  const src = fn.toString();
+  const match = src.match(/^(?:async\s+)?function\s*\w*\s*\(([^)]*)\)/);
+  if (!match) {
+    return [];
+  }
+  return match[1]
+    .split(",")
+    .map((p) => p.trim().replace(/[:=?].*/s, "").trim())
+    .filter(Boolean);
+}
+
+function spreadArgs(
+  fn: Function,
+  data: Record<string, unknown>,
+): unknown[] {
+  const names = extractParamNames(fn);
+  if (names.length === 0) {
+    return [];
+  }
+  return names.map((name) => data[name]);
+}
+
+async function run(
+  agentPath: string,
+  agentFunc: string,
+  agentData: Record<string, unknown>,
+): Promise<void> {
+  const mod = await import(pathToFileURL(agentPath).href);
+
+  if (typeof mod[agentFunc] !== "function") {
+    throw new Error(`No module function '${agentFunc}' at '${agentPath}'`);
+  }
+
+  const fn = mod[agentFunc] as Function;
+  const args = spreadArgs(fn, agentData);
+  const value = await fn(...args);
+  returnToLlm(value);
+  dumpResult(`{agent_name}:${agentFunc}`);
+}
+
+function returnToLlm(value: unknown): void {
+  if (value === null || value === undefined) {
+    return;
+  }
+
+  const output = process.env["LLM_OUTPUT"];
+  const write = (s: string) => {
+    if (output) {
+      writeFileSync(output, s, "utf-8");
+    } else {
+      process.stdout.write(s);
+    }
+  };
+
+  if (typeof value === "string" || typeof value === "number" || typeof value === "boolean") {
+    write(String(value));
+  } else if (typeof value === "object") {
+    write(JSON.stringify(value, null, 2));
+  }
+}
+
+function dumpResult(name: string): void {
+  const dumpResults = process.env["LLM_DUMP_RESULTS"];
+  const llmOutput = process.env["LLM_OUTPUT"];
+
+  if (!dumpResults || !llmOutput || !process.stdout.isTTY) {
+    return;
+  }
+
+  try {
+    const pattern = new RegExp(`\\b(${dumpResults})\\b`);
+    if (!pattern.test(name)) {
+      return;
+    }
+  } catch {
+    return;
+  }
+
+  let data: string;
+  try {
+    data = readFileSync(llmOutput, "utf-8");
+  } catch {
+    return;
+  }
+
+  process.stdout.write(
+    `\x1b[2m----------------------\n${data}\n----------------------\x1b[0m\n`,
+  );
+}
+
+main().catch((err) => {
+  process.stderr.write(`${err}\n`);
+  process.exit(1);
+});

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)
@@ -49,6 +49,11 @@ def parse_raw_data(data):
 
 
 def parse_argv():
+    tool_data_file = os.environ.get("LLM_TOOL_DATA_FILE")
+    if tool_data_file and os.path.isfile(tool_data_file):
+        with open(tool_data_file, "r", encoding="utf-8") as f:
+            return f.read()
+
     argv = sys.argv[:] + [None] * max(0, 2 - len(sys.argv))
 
     tool_data = argv[1]
@@ -60,11 +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

@@ -13,7 +13,11 @@ main() {
 }
 
 parse_argv() {
-		tool_data="$1"
+    if [[ -n "$LLM_TOOL_DATA_FILE" ]] && [[ -f "$LLM_TOOL_DATA_FILE" ]]; then
+        tool_data="$(cat "$LLM_TOOL_DATA_FILE")"
+    else
+				tool_data="$1"
+    fi
     if [[ -z "$tool_data" ]]; then
         die "usage: ./{function_name}.sh <tool-data>"
     fi
@@ -25,6 +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() {
@@ -54,7 +59,6 @@ run() {
     if [[ "$OS" == "Windows_NT" ]]; then
         set -o igncr
         tool_path="$(cygpath -w "$tool_path")"
-        tool_data="$(echo "$tool_data" | sed 's/\\/\\\\/g')"
     fi
 
     jq_script="$(cat <<-'EOF'
@@ -67,11 +71,11 @@ def to_args:
     to_entries | .[] |
     (.key | split("_") | join("-")) as $key |
     if .value | type == "array" then
-        .value | .[] | "--\($key) \(. | escape_shell_word)"
+        .value | .[] | "--\($key)=\(. | escape_shell_word)"
     elif .value | type == "boolean" then
         if .value then "--\($key)" else "" end
     else
-        "--\($key) \(.value | escape_shell_word)"
+        "--\($key)=\(.value | escape_shell_word)"
     end;
 [ to_args ] | join(" ")
 EOF

assets/functions/scripts/run-tool.ts

@@ -0,0 +1,185 @@
+#!/usr/bin/env tsx
+
+// Usage: ./{function_name}.ts <tool-data>
+
+import { readFileSync, writeFileSync, existsSync } from "fs";
+import { join } from "path";
+import { pathToFileURL } from "url";
+
+async function main(): Promise<void> {
+  const rawData = parseArgv();
+  const toolData = parseRawData(rawData);
+
+  const rootDir = "{root_dir}";
+  setupEnv(rootDir, rawData);
+
+  const toolPath = "{tool_path}.ts";
+  await run(toolPath, "run", toolData);
+}
+
+function parseRawData(data: string): Record<string, unknown> {
+  if (!data) {
+    throw new Error("No JSON data");
+  }
+
+  try {
+    return JSON.parse(data);
+  } catch {
+    throw new Error("Invalid JSON data");
+  }
+}
+
+function parseArgv(): string {
+  const toolDataFile = process.env["LLM_TOOL_DATA_FILE"];
+  if (toolDataFile && existsSync(toolDataFile)) {
+    return readFileSync(toolDataFile, "utf-8");
+  }
+
+  const toolData = process.argv[2];
+
+  if (!toolData) {
+    process.stderr.write("Usage: ./{function_name}.ts <tool-data>\n");
+    process.exit(1);
+  }
+
+  return toolData;
+}
+
+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 {
+  let lines: string[];
+  try {
+    lines = readFileSync(filePath, "utf-8").split("\n");
+  } catch {
+    return;
+  }
+
+  for (const raw of lines) {
+    const line = raw.trim();
+    if (line.startsWith("#") || !line) {
+      continue;
+    }
+
+    const eqIdx = line.indexOf("=");
+    if (eqIdx === -1) {
+      continue;
+    }
+
+    const key = line.slice(0, eqIdx).trim();
+    if (key in process.env) {
+      continue;
+    }
+
+    let value = line.slice(eqIdx + 1).trim();
+    if (
+      (value.startsWith('"') && value.endsWith('"')) ||
+      (value.startsWith("'") && value.endsWith("'"))
+    ) {
+      value = value.slice(1, -1);
+    }
+    process.env[key] = value;
+  }
+}
+
+function extractParamNames(fn: Function): string[] {
+  const src = fn.toString();
+  const match = src.match(/^(?:async\s+)?function\s*\w*\s*\(([^)]*)\)/);
+  if (!match) {
+    return [];
+  }
+  return match[1]
+    .split(",")
+    .map((p) => p.trim().replace(/[:=?].*/s, "").trim())
+    .filter(Boolean);
+}
+
+function spreadArgs(
+  fn: Function,
+  data: Record<string, unknown>,
+): unknown[] {
+  const names = extractParamNames(fn);
+  if (names.length === 0) {
+    return [];
+  }
+  return names.map((name) => data[name]);
+}
+
+async function run(
+  toolPath: string,
+  toolFunc: string,
+  toolData: Record<string, unknown>,
+): Promise<void> {
+  const mod = await import(pathToFileURL(toolPath).href);
+
+  if (typeof mod[toolFunc] !== "function") {
+    throw new Error(`No module function '${toolFunc}' at '${toolPath}'`);
+  }
+
+  const fn = mod[toolFunc] as Function;
+  const args = spreadArgs(fn, toolData);
+  const value = await fn(...args);
+  returnToLlm(value);
+  dumpResult("{function_name}");
+}
+
+function returnToLlm(value: unknown): void {
+  if (value === null || value === undefined) {
+    return;
+  }
+
+  const output = process.env["LLM_OUTPUT"];
+  const write = (s: string) => {
+    if (output) {
+      writeFileSync(output, s, "utf-8");
+    } else {
+      process.stdout.write(s);
+    }
+  };
+
+  if (typeof value === "string" || typeof value === "number" || typeof value === "boolean") {
+    write(String(value));
+  } else if (typeof value === "object") {
+    write(JSON.stringify(value, null, 2));
+  }
+}
+
+function dumpResult(name: string): void {
+  const dumpResults = process.env["LLM_DUMP_RESULTS"];
+  const llmOutput = process.env["LLM_OUTPUT"];
+
+  if (!dumpResults || !llmOutput || !process.stdout.isTTY) {
+    return;
+  }
+
+  try {
+    const pattern = new RegExp(`\\b(${dumpResults})\\b`);
+    if (!pattern.test(name)) {
+      return;
+    }
+  } catch {
+    return;
+  }
+
+  let data: string;
+  try {
+    data = readFileSync(llmOutput, "utf-8");
+  } catch {
+    return;
+  }
+
+  process.stdout.write(
+    `\x1b[2m----------------------\n${data}\n----------------------\x1b[0m\n`,
+  );
+}
+
+main().catch((err) => {
+  process.stderr.write(`${err}\n`);
+  process.exit(1);
+});

assets/functions/tools/demo_py.py

@@ -1,6 +1,7 @@
 import os
 from typing import List, Literal, Optional
 
+
 def run(
     string: str,
     string_enum: Literal["foo", "bar"],
@@ -9,26 +10,38 @@ def run(
     number: float,
     array: List[str],
     string_optional: Optional[str] = None,
+    integer_with_default: int = 42,
+    boolean_with_default: bool = True,
+    number_with_default: float = 3.14,
+    string_with_default: str = "hello",
     array_optional: Optional[List[str]] = None,
 ):
-    """Demonstrates how to create a tool using Python and how to use comments.
+    """Demonstrates all supported Python parameter types and variations.
     Args:
-        string: Define a required string property
-        string_enum: Define a required string property with enum
-        boolean: Define a required boolean property
-        integer: Define a required integer property
-        number: Define a required number property
-        array: Define a required string array property
-        string_optional: Define an optional string property
-        array_optional: Define an optional string array property
+        string: A required string property
+        string_enum: A required string property constrained to specific values
+        boolean: A required boolean property
+        integer: A required integer property
+        number: A required number (float) property
+        array: A required string array property
+        string_optional: An optional string property (Optional[str] with None default)
+        integer_with_default: An optional integer with a non-None default value
+        boolean_with_default: An optional boolean with a default value
+        number_with_default: An optional number with a default value
+        string_with_default: An optional string with a default value
+        array_optional: An optional string array property
     """
     output = f"""string: {string}
 string_enum: {string_enum}
-string_optional: {string_optional}
 boolean: {boolean}
 integer: {integer}
 number: {number}
 array: {array}
+string_optional: {string_optional}
+integer_with_default: {integer_with_default}
+boolean_with_default: {boolean_with_default}
+number_with_default: {number_with_default}
+string_with_default: {string_with_default}
 array_optional: {array_optional}"""
 
     for key, value in os.environ.items():

assets/functions/tools/demo_ts.ts

@@ -0,0 +1,53 @@
+/**
+ * Demonstrates all supported TypeScript parameter types and variations.
+ *
+ * @param string - A required string property
+ * @param string_enum - A required string property constrained to specific values
+ * @param boolean - A required boolean property
+ * @param number - A required number property
+ * @param array_bracket - A required string array using bracket syntax
+ * @param array_generic - A required string array using generic syntax
+ * @param string_optional - An optional string using the question mark syntax
+ * @param string_nullable - An optional string using the union-with-null syntax
+ * @param number_with_default - An optional number with a default value
+ * @param boolean_with_default - An optional boolean with a default value
+ * @param string_with_default - An optional string with a default value
+ * @param array_optional - An optional string array using the question mark syntax
+ */
+export function run(
+  string: string,
+  string_enum: "foo" | "bar",
+  boolean: boolean,
+  number: number,
+  array_bracket: string[],
+  array_generic: Array<string>,
+  string_optional?: string,
+  string_nullable: string | null = null,
+  number_with_default: number = 42,
+  boolean_with_default: boolean = true,
+  string_with_default: string = "hello",
+  array_optional?: string[],
+): string {
+  const parts = [
+    `string: ${string}`,
+    `string_enum: ${string_enum}`,
+    `boolean: ${boolean}`,
+    `number: ${number}`,
+    `array_bracket: ${JSON.stringify(array_bracket)}`,
+    `array_generic: ${JSON.stringify(array_generic)}`,
+    `string_optional: ${string_optional}`,
+    `string_nullable: ${string_nullable}`,
+    `number_with_default: ${number_with_default}`,
+    `boolean_with_default: ${boolean_with_default}`,
+    `string_with_default: ${string_with_default}`,
+    `array_optional: ${JSON.stringify(array_optional)}`,
+  ];
+
+  for (const [key, value] of Object.entries(process.env)) {
+    if (key.startsWith("LLM_")) {
+      parts.push(`${key}: ${value}`);
+    }
+  }
+
+  return parts.join("\n");
+}

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 --include File pattern to filter by (e.g. "*.rs", "*.{ts,tsx}", "*.py")
+# @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"). 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
-        echo "Error: directory not found: $search_path" >> "$LLM_OUTPUT"
+    if [[ ! -e "$search_path" ]]; then
+        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+=(
-        --exclude-dir='.git'
-        --exclude-dir='node_modules'
-        --exclude-dir='target'
-        --exclude-dir='dist'
-        --exclude-dir='build'
-        --exclude-dir='__pycache__'
-        --exclude-dir='vendor'
-        --exclude-dir='.build'
-        --exclude-dir='.next'
-        --exclude='*.min.js'
-        --exclude='*.min.css'
-        --exclude='*.map'
-        --exclude='*.lock'
-        --exclude='package-lock.json'
-    )
-
-    if [[ -n "$include_filter" ]]; then
-        grep_args+=("--include=$include_filter")
+    if [[ -d "$search_path" ]]; then
+        # Use -r (not -R) so symlinks to directories are NOT followed - this avoids
+        # infinite loops on pathological symlink cycles (e.g. `ln -s . loop`).
+        grep_args+=(-r)
+        grep_args+=(
+            --exclude-dir='.git'
+            --exclude-dir='node_modules'
+            --exclude-dir='target'
+            --exclude-dir='dist'
+            --exclude-dir='build'
+            --exclude-dir='__pycache__'
+            --exclude-dir='vendor'
+            --exclude-dir='.build'
+            --exclude-dir='.next'
+            --exclude='*.min.js'
+            --exclude='*.min.css'
+            --exclude='*.map'
+            --exclude='*.lock'
+            --exclude='package-lock.json'
+        )
+        if [[ -n "$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.
-# This can be used to edit a file without having to rewrite the whole file.
+# @describe Apply a unified-diff patch to a file at the specified path. Use this for editing an existing file. It's the
+# 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.
-# Prefer this over fs_cat for controlled reading. Use offset/limit to read specific sections.
+# @describe Read a TRUNCATED view of a file with line numbers, offset, and limit. For directories, lists entries.
+# 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/get_current_weather.ts

@@ -0,0 +1,24 @@
+#!/usr/bin/env tsx
+
+import { appendFileSync, mkdirSync } from "fs";
+import { dirname } from "path";
+
+/**
+ * Get the current weather in a given location
+ * @param location - The city and optionally the state or country (e.g., "London", "San Francisco, CA").
+ */
+export async function run(location: string): string {
+  const encoded = encodeURIComponent(location);
+  const url = `https://wttr.in/${encoded}?format=4`;
+
+  const resp = await fetch(url);
+  const data = await resp.text();
+
+  const dest = process.env["LLM_OUTPUT"] ?? "/dev/stdout";
+  if (dest !== "-" && dest !== "/dev/stdout") {
+    mkdirSync(dirname(dest), { recursive: true });
+    appendFileSync(dest, data, "utf-8");
+  }
+
+  return data;
+}

assets/functions/tools/query_jira_issues.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-set -e
-
-# @meta require-tools jira
-# @describe Query for jira issues using a Jira Query Language (JQL) query
-# @option --jql-query! The Jira Query Language query to execute
-# @env LLM_OUTPUT=/dev/stdout The output path
-
-main() {
-  jira issue ls -q "$argc_jql_query" --plain >> "$LLM_OUTPUT"
-}

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

@@ -121,7 +121,7 @@ _cursor_blink_off() {
 }
 
 _cursor_to() {
-  echo -en "\033[$1;$2H" >&2
+  echo -en "\033[$1;${2:-1}H" >&2
 }
 
 # shellcheck disable=SC2154
@@ -133,7 +133,7 @@ _key_input() {
     _read_stdin -rsn2 b
   fi
 
-  declare input="${a}${b}"
+  declare input="${a}${b:-}"
   case "$input" in
     "${ESC}[A" | "k") echo up ;;
     "${ESC}[B" | "j") echo down ;;
@@ -506,16 +506,16 @@ open_link() {
 }
 
 guard_operation() {
-  if [[ -t 1 ]]; then
-  	if [[ -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
-			ans="$(confirm "${1:-Are you sure you want to continue?}")"
+	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
+		# 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 [[ "$ans" == 0 ]]; then
-				error "Operation aborted!" 2>&1
-				exit 1
-			fi
+		if [[ "$ans" == 0 ]]; then
+			error "Operation aborted!" 2>&1
+			exit 1
 		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")"
-    confirmation_prompt="$2"
+	path="$(_to_real_path "$1")"
+	confirmation_prompt="$2"
 
-    if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
-			ans="$(confirm "$confirmation_prompt")"
+	if [[ ! "$path" == "$(pwd)"* && -z "$AUTO_CONFIRM" && -z "$LLM_AGENT_VAR_AUTO_CONFIRM" ]]; then
+		# 2>/dev/tty: see guard_operation — prevents prompt text leaking via captured stderr.
+		ans="$(confirm "$confirmation_prompt" 2>/dev/tty)"
 
-			if [[ "$ans" == 0 ]]; then
-				error "Operation aborted!" >&2
-				exit 1
-			fi
-    fi
-  fi
+		if [[ "$ans" == 0 ]]; then
+			error "Operation aborted!" >&2
+			exit 1
+		fi
+	fi
 }
 
 _to_real_path() {

assets/roles/atlassian.md

@@ -0,0 +1,8 @@
+---
+enabled_mcp_servers: atlassian
+---
+You are the librarian for the company's Confluence and Jira knowledge bases. Your job is to help users find and retrieve
+information from these platforms. Use all tools at your disposal to answer user queries.
+
+Available Tools:
+{{__tools__}}

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/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 +1,336 @@
+# 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
+        . "$HOME/.cargo/env"
+        cargo install --locked coyote-ai
+      user: '1000'
+      description: Install Coyote AI CLI via Rust's Cargo
+
+  startup:
+    - command:
+        [
+          'sh',
+          '-c',
+          'test -f "$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** for potential continuation.
+
+## 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/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/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