Skill Claude CodeCodex
Ask Claude Code to audit a file or set of files and return structured findings. Claude reads the code with fresh eyes and independent judgment — Codex does not self-review. Supports mini (5-dimension) and full (9-dimension) depth.
Skill Claude CodeCodex
Canonical reference for Claude Code plugin artifact schemas, hook events, frontmatter fields, and naming conventions. Used to inject domain knowledge into Codex audit prompts. Run /cc-suite:refresh-knowledge to update from latest docs.
Skill Claude CodeCodex
Send a bug or failing test to Claude Code for root-cause analysis and fix. Use when you've hit an error you can't trace, a test is failing for unclear reasons, or a behavior is wrong and the cause is deep in the codebase.
Skill Claude CodeCodex
Delegate an implementation task to Claude Code. Use when you want Claude to write, edit, or refactor code directly in the project. Claude has full read/write access and will make the changes autonomously.
Skill Claude CodeCodex
Ask Claude Code to produce an implementation plan before you write code. Use when the task is complex, touches multiple files, or has unclear requirements. Claude returns a numbered step-by-step plan with file paths and interfaces — you implement it.
Skill Claude CodeCodex
Delegate a code review task to Claude Code via the claudecode MCP tool. Use when you want Claude's judgment on architecture, security, correctness, test coverage, or code quality for files you've just written or modified.
Skill Claude CodeCodex
Diagnose the cc-suite setup in the current project. Runs the full health check, explains every issue, and fixes what can be fixed automatically. Skill counterpart to /cc-suite:diagnose.
Skill Claude CodeCodex
Initialize cc-suite for the current project — sets up the AGENTS.md bridge, registers Codex, Claude, and Antigravity MCP surfaces, and generates a .cc-suite.md config. Skill counterpart to /cc-suite:init.
Skill Claude CodeCodex
Non-interactive re-run of all cc-suite bridge and registration scripts. No questions asked — idempotent escalation step after the diagnose skill finds issues it could not fix. Skill counterpart to /cc-suite:repair.
Skill Claude CodeCodex
Ask Claude Code to verify that a list of reported issues has been fixed. Continues the same Claude session from a prior audit if sessionid is available, so Claude has full context of what it flagged. Returns FIXED / NOT FIXED / PARTIAL / REGRESSED per issue.
Skill Claude CodeCodex
Use when writing, reviewing, or naming any cc-suite artifact — pick the canonical noun or verb from this registry rather than coining a synonym. Loaded by NLPM's scorer and checker when R51 is enabled in .claude/nlpm.local.md.
Agent
Reviews code for readability over correctness. Consult on PRs, new modules, or any code a reader will need to follow without context. Context: Claude has finished a refactor and wants a fresh pair of eyes on whether the new structure reads cleanly. user: "Here's the refactored auth module — does it still make sense to…
Agent
Finds code that can be removed. Consult before adding new abstractions, when the codebase feels heavy, or during periodic cleanup. Context: Claude has been asked to refactor a module that has accumulated cruft over a year. user: "The notifications module feels bloated — refactor it." assistant: "Before I touch…
Agent
Judges whether docs do their job — orient a new reader, explain WHY not WHAT, stay honest about scope. Consult on READMEs, PRs, architecture notes. Context: Claude has rewritten the project README and wants a second opinion before publishing. user: "Review the new README for whether it actually helps a first-time…
Agent
Reminds the caller of the project's overarching priorities. Consult before architectural decisions or when scope is drifting. Context: Claude is about to add a config-driven plugin system to a tool whose pitch is "do one thing well". user: "I'm planning to add a YAML-based plugin loader so users can extend the audit…
Plugin Claude Code
Plugin marketplace listing 1 plugin: bureau.
Plugin Claude Code
Turn AI sessions into a maintained, inspectable canon. Capture each session to append-only logbooks, compile them into a consistency-checked knowledge base (cabinets) gated by a human review tier, and render it as a navigable offline gazette (built by the bundled press). A typed review queue (gazette review) orders…
Agent Claude Code
You are bureau's Auditor — an independent, read-only reviewer of this repo's knowledge base. You do not write, edit, or fix anything. You find what's wrong and report it precisely, with the page and its trust tier, so a human can route the fix through the gate.
Instructions file
Claude Code instructions for xiaolai/bureau, covering bureau — plugin development, prerequisites, build & run, test and plugin structure.
Command
Record an architecture decision — scaffold a proposed MADR ADR page (auto-numbered, optionally superseding a prior one) into the canon. Authors only; a human approves it via bureau:review.
Command
Bulk-approve the whole approvable review backlog as canonical, in one confirmation. Shows exactly what would be promoted, confirms in-session, then hands you the single pre-filled gazette approve --all --by human line to fire as yourself. The AI never signs --by human for you — you run the one line, so the log's human…
Command
Let Codex (via cc-suite) deliberate over the bureau review queue as your representative — it reads each unapproved claim and recommends approve or hold, then either hands you the exact approve command (advisor, default) or, only where the workspace opted in, commits under its own codex authority (delegate).
Command
Distil minutes into consistency-checked dossiers (the canon), with provenance back to each session.
Command
Manage bureau's crew — list, enable, or author specialized agents that work the canon.