docs: Added documentation for the new adversary and adversarial-review skill

Agents.md

@@ -823,6 +823,14 @@ available; only the auto-injected prompt text is suppressed.
 # Built-In Agents
 Coyote comes packaged with some useful built-in agents:
 
+* `adversary`: An adversarial plan-conformance reviewer. Where `code-reviewer` asks "is this code good?",
+   `adversary` asks "is this the code the plan asked for — all of it, and only it?". Given a diff plus the
+   task/plan's acceptance criteria, it maps every criterion to evidence in the diff and hunts for silently
+   skipped criteria, scope drift, interface substitution, and requirements that never landed ("the dog that
+   didn't bark"), returning a blocking `ADVERSARIAL_REVIEW: CONFORMS`/`DIVERGES` verdict (via the
+   `adversarial-review` skill). The post-implementation counterpart to `oracle`'s pre-implementation
+   `plan-review`. Designed to be delegated to by `sisyphus` alongside `code-reviewer` (they cover different
+   failure modes: quality vs. conformance).
 * `coder`: An agent to assist you with all your coding tasks
 * `code-reviewer`: A [CodeRabbit](https://coderabbit.ai)-style code reviewer that spawns per-file reviewers using the 
    teammate messaging pattern
@@ -838,9 +846,10 @@ Coyote comes packaged with some useful built-in agents:
 * `report-writer`: An agent to polish research findings into clear, citation-preserving final reports
 * `sisyphus`: A powerhouse orchestrator agent for writing complex code and acting as a natural language interface for 
    your codebase (similar to ClaudeCode, Gemini CLI, Codex, or OpenCode). Uses sub-agent spawning to delegate to 
-   `explore`, `librarian`, `coder`, `oracle`, and `step-runner`. Also supports plan-driven workflows: authoring phased 
+   `explore`, `librarian`, `coder`, `oracle`, `code-reviewer`, `adversary`, and `step-runner`. On non-trivial work it 
-   implementation plans (via the `plan-authoring` skill), having `oracle` review them, and executing them one reviewed 
+   runs two complementary independent review passes — `code-reviewer` for code quality and `adversary` for plan 
-   step at a time.
+   conformance. Also supports plan-driven workflows: authoring phased implementation plans (via the `plan-authoring` 
+   skill), having `oracle` review them, and executing them one reviewed step at a time.
 * `sql`: A universal SQL agent that enables you to talk to any relational database in natural language
 * `step-runner`: A graph-based agent that executes ONE step of a phased implementation plan (a `plans/` repo authored 
    with the `plan-authoring` skill) with the step protocol enforced as graph edges: orient from the previous handoff -> 

Skills.md

@@ -378,7 +378,7 @@ whitelist — but their processes stay cached for fast re-load.
 
 # Built-in Skills
 
-Coyote ships with fourteen built-in skills, installed automatically on first run:
+Coyote ships with fifteen built-in skills, installed automatically on first run:
 
 | Skill                 | Granted tools / MCP servers                                              | Purpose                                                                     |
 |-----------------------|--------------------------------------------------------------------------|------------------------------------------------------------------------------|
@@ -393,6 +393,7 @@ Coyote ships with fourteen built-in skills, installed automatically on first run
 | `verification-gates`  | `execute_command`                                                        | Evidence requirements (diagnostics, builds, tests) before claiming completion. |
 | `plan-authoring`      | `fs_read, fs_grep, fs_glob, fs_ls, fs_cat, fs_write`                     | Author executable high-level plans and per-step implementation plans for phased work; defines the plan repo layout and step-plan schema. |
 | `plan-review`         | `fs_read, fs_grep, fs_glob, fs_ls, fs_cat`                               | Adversarial review of implementation plans against executability, verifiability, and completeness standards. |
+| `adversarial-review`  | `fs_read, fs_grep, fs_glob, fs_cat, fs_ls`                               | Adversarial plan-conformance review of an *implementation* against the plan it should satisfy (skipped criteria, scope drift, interface substitution); verdict `CONFORMS`/`DIVERGES`. Complements `code-review` (quality) and is the post-implementation counterpart to `plan-review`. |
 | `step-implementation` | `execute_command`                                                        | End-to-end protocol for executing one step of a phased implementation plan. |
 | `handoff-protocol`    | `fs_read, fs_cat, fs_ls, fs_write`                                       | Schema and discipline for writing and reading step handoff documents between implementation steps. |
 | `iwe-knowledge-base`  | MCP server: `iwe`                                                        | Navigate and curate large markdown knowledgebases (plans, specs, notes) via [IWE](https://github.com/iwe-org/iwe) graph tools. Requires the `iwec` binary. |
@@ -450,4 +451,4 @@ When skills are enabled, the model has three tools available for managing them i
 These are how the model discovers and uses skills mid-conversation. You can disable this discovery channel by setting
 `skills_enabled: false` at any level; the three tools then disappear from the model's function list entirely. The same
 happens if `function_calling_support: false` is set globally. Without function calling, the skill system has no surface
-to operate on, so it is silently disabled across REPL, CLI, agents, and the model's tool list.
+to operate on, so it is silently disabled across REPL, CLI, agents, and the model's tool list.