Read-only MCP server for AI coding agents: repo inspection, skill routing, code audits, docs evidence checks, and issue/PR planning.
This repository also configures its own agents. See what codeaudit tells them →
Skill Claude CodeCodex
Use when model providers, agents, RAG, tools, AI SDKs, prompt injection, tool-call safety, retrieval grounding, provider error leakage, or telemetry redaction matter.
Skill Claude CodeCodex
Use when initializing, auditing, refactoring, securing, documenting, testing, planning, or preparing PR workflows for a software repository with CodeAudit project detection and skill routing.
Skill Claude CodeCodex
Use when an AI coding agent needs to inspect a repository, choose the right workflow, audit code/docs/tests/skills, improve Python or TypeScript projects, plan issues or PRs, or use the CodeAudit MCP server.
Skill Claude CodeCodex
Use when reviewing README or docs truthfulness, recruiter-facing claims, security claims, production-readiness claims, evidence maps, or unsupported project claims.
Skill Claude CodeCodex
Use when auditing, reviewing, refactoring, or planning improvements to application or infrastructure code that needs maintainability, typed boundaries, tests, or simpler architecture.
Skill Claude CodeCodex
Use when generating GitHub issue plans, PR plans, branch names, commit scopes, review checklists, merge guidance, or issue-first workflow guidance.
Skill Claude CodeCodex
Use when a Next.js project or security audit involves App Router, route handlers, middleware, auth, validation, headers, environment variables, deployment, logging, redirects, SSRF, uploads, or rate limits.
Skill Claude CodeCodex
Use when current framework, SDK, API, MCP, cloud, security, or version-specific behavior matters and implementation decisions need official documentation grounding.
Skill Claude CodeCodex
Use when reviewing, creating, or improving Python services, CLIs, libraries, FastAPI, Django, Flask, pytest, uv, pyproject, typing, Pydantic, SQLAlchemy, async code, packaging, or deployment.
Skill Claude CodeCodex
Use when creating, auditing, or improving Python MCP servers, FastMCP tools, resources, prompts, stdio transports, streamable HTTP transports, MCP Inspector setup, or Python tool schemas.
Skill Claude CodeCodex
Use when splitting files, improving architecture, reducing duplication, changing internals, or preserving behavior through focused tests during refactors.
Skill Claude CodeCodex
Use when reviewing installed skills, adding third-party skills, hardening agent workflows, checking skill correctness, removing duplicate skills, or investigating supply-chain, prompt-injection, secret-leakage, dependency-install, webhook, destructive-shell, manifest-quality, or resource-discovery risks.
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: