An operating system for Claude Code. Skills, hooks (MCR), and a lean-context framework for smarter AI coding sessions.
Skill Claude Code
Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.
Skill Claude Code
Run a security audit and dependency check on project dependencies. Use when you want to check for vulnerabilities, audit packages, or update outdated dependencies.
Skill Claude Code
Run a comprehensive codebase hygiene audit. Spawns a team of recon and research agents to analyze structure, dependencies, inconsistencies, and industry best practices, then synthesizes findings into an actionable refactoring plan with phased implementation.
Skill Claude Code
Review a pull request for correctness, convention compliance, and test coverage. Use when you want to review a PR, check code quality, or get feedback on changes before merging.
Skill Claude Code
API development conventions and patterns. Applies when writing or modifying API routes, MCP tools, or CLI commands -- covers authentication, ownership enforcement, error responses, and route organization.
Skill Claude Code
Dashboard/frontend development conventions -- vanilla HTML/JS/CSS patterns, theming, and API integration. Applies when modifying frontend files.
Skill Claude Code
Guide through a database schema change. Use when you need to modify the database schema, add columns, create tables, or run migrations.
Skill Claude Code
Update architecture documentation after code changes to keep docs in sync with reality. Use when structural changes have been made and documentation needs updating.
Skill Claude Code
Fix a GitHub issue end-to-end -- read the issue, implement the fix, write tests, and create a commit. Use when you want to fix a specific GitHub issue, resolve a bug report, or implement a feature request.
Skill Claude Code
Scaffold a new REST API endpoint. Use when adding a new API route or extending the REST API with new functionality.
Skill Claude Code
Add a new MCP tool to a FastMCP server. Use when adding a new tool for LLM agents or extending the MCP interface with new functionality.
Skill Claude Code
Run the full CI pipeline locally -- linting, type checking, and tests. Use before commits or deployments to verify everything passes.
Skill Claude Code
Check the current deployment status, health, and recent CI runs. Use when you want to know if the service is up, check recent CI/CD activity, or diagnose deployment issues.
Skill Claude Code
Deploy to production. Runs pre-deploy safety checks, pushes to trigger CI/CD, and monitors the deployment.
Skill Claude Code
Guide through security incident or outage response. Use when there is a security incident, the service is down, or there is a production emergency.
Skill Claude CodeCodex needs its repo
Memory consolidation skill for Claude Code. Scans session transcripts for corrections, decisions, preferences, and patterns, then merges findings into persistent memory files. Auto-triggers via native Stop hook every 24hrs. Inspired by how sleep consolidates human memory.
Skill Claude Code
Guided ideation with built-in feasibility research. Conversation with the user to explore ideas, research agents validate practicality, then resolve into a requirements doc for /plan-features.
Skill Claude Code
Adversarial 5-agent debate to evaluate what you have. Critics attack, defenders respond, moderator writes verdict. Produces a readiness report -- feed into /plan-features to act on findings.
Skill Claude Code
Execute an execution plan document by orchestrating worktree agents, enforcing commit/merge/test gates, and tracking progress. Main agent stays lean -- all work delegated.
Skill Claude Code
Structured debate -> plan -> execute pipeline for evaluating feature readiness. Runs 5-agent debate, creates action plan with review, then executes fixes.
Skill Claude Code
Generate execution plan documents for multi-team agent work. Analyzes file conflicts, builds dependency graphs, and produces structured plans that drive flawless parallel execution.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: