directives_auditlisted

# directives_audit — validate AI-agent guidance files Before an agent works on a repo, it should know which directives exist, whether they are healthy, and — most importantly — whether they exist at all. Inspired by shadcn/improve's "recon" step (ingest intent docs so decided tradeoffs aren't re-flagged). ## When to use - Checking if a project has **any** agent instructions (CLAUDE.md / AGENTS.md / …). - Auditing existing directives for **staleness, size, format or conflicts**. - Onboarding to an unfamiliar repo — map its instructions, intent docs and specs. - The user mentions CLAUDE.md, AGENTS.md, agent rules, specs, or "directives". ## Run it ```bash python -m skills.directives_audit.cli <project_dir> # readable report python -m skills.directives_audit.cli <project_dir> --json # machine-readable ``` ```python from skills.directives_audit import audit report = audit("/path/to/project") report["has_instructions"] # bool — the big one report["score"] # 0-100 directive health report["findings"] # severity, path, message, fix_hint ``` ## What it detects | Tool / purpose | Files | |----------------|-------| | Claude Code | `CLAUDE.md`, `CLAUDE.local.md`, `.claude/`, `.mcp.json` | | Codex / OpenCode / generic | `AGENTS.md`, `.agents/**` | | Cursor | `.cursorrules`, `.cursor/rules/**.mdc` | | GitHub Copilot | `.github/copilot-instructions.md`, `.github/instructions/**` | | Gemini / Antigravity | `GEMINI.md`, `.gemini/**` | | Windsurf / C