Audit the repository, not just two files.
Use this checklist when adopting AGENTS.md, consolidating CLAUDE.md, or reviewing a repository used by several coding agents. A careful first pass usually takes 30–60 minutes.
Published August 2, 2026 · Maintained by AgentsMD CheckerUse it with your team
Work from a clean checkout, record evidence beside each item, and open a pull request for instruction changes so the same review rules apply as code.
Download Markdown checklist1. Inventory and scope
- Find every instruction file
Search the repository for AGENTS.md, CLAUDE.md, CLAUDE.local.md, tool-specific rule files, and nested copies. Record which directory each file governs.
- Map precedence
Write down the order in which each coding agent discovers root, parent, nested, local, and user-level instructions. Do not assume two tools merge files the same way.
- Choose one shared contract
Decide which committed file owns cross-tool rules. AGENTS.md is a practical default when several coding agents work in the same repository.
2. References and commands
- Resolve every path
Verify that referenced source folders, architecture documents, fixtures, scripts, and generated directories still exist with the same casing.
- Run setup from a clean checkout
Test the documented package-manager and setup commands without relying on an existing node_modules folder or uncommitted local configuration.
- Run every quality gate
Execute the exact lint, typecheck, test, build, and formatting commands named in the instructions. Remove commands that no longer exist.
- Check command consistency
Flag npm versus pnpm, duplicated flags, obsolete workspace filters, and different test commands across instruction files.
3. Conflicts and context quality
- Compare positive and negative rules
Look for pairs such as always push versus never push, ask first versus proceed automatically, or edit generated files versus never edit them.
- Remove duplicated prose
Keep a shared rule in one canonical place. Tool overlays should contain only real tool-specific exceptions.
- Replace vague preferences
Turn 'write good tests' into an observable expectation: which tests, where they live, and when they must run.
- Trim stale context
Delete historic explanations that do not change an agent's current decision. Link to durable documentation when background is still useful.
4. Safety and delivery
- Protect secrets and production
State where secrets may live, what must never be committed, and which production systems require explicit approval.
- Separate guidance from enforcement
Use repository permissions, CI, hooks, branch protection, and deployment controls for boundaries that cannot depend on model compliance.
- Define destructive actions
Name operations that require confirmation, including data deletion, schema rollback, force push, broad file rewrites, and production changes.
- Define done
List the evidence required before handoff: relevant tests, build status, changed behavior, migrations, documentation, and remaining external setup.
5. Multi-agent maintenance
- Test each supported agent
Run the same small repository task with every supported coding agent and note which instructions it actually discovers.
- Keep overlays thin
Import or reference the shared contract where the tool supports it, then add only the minimum agent-specific behavior.
- Assign an owner and review trigger
Name who updates the instructions and require a review when commands, directories, CI, deployment, or supported agents change.
Fastest next step
Start with the free CLAUDE.md vs AGENTS.md checker. It catches file-level drift in the browser. Use the full checklist for paths, commands, nested scope, and enforcement boundaries that a text comparison cannot verify.