Need AI Training/Help?CloudYeti.io/meet
MarkdownMe
Agent instruction guide

CLAUDE.md Missing Commands Checklist

Check whether a CLAUDE.md includes the build, test, lint, dev server, deploy, and verification commands an agent needs before editing.

Direct answer

A useful CLAUDE.md should list the commands an agent needs to work safely: install, dev server, lint, typecheck, test, build, deploy, formatting, and any special environment or profile commands. If those are missing, the agent has to guess, which leads to skipped verification and broken handoffs.

Open CLAUDE.md Reviewer

When to use this

  • A generated CLAUDE.md only describes the stack but not commands.
  • Agents keep asking how to run tests or builds.
  • The repo has special profiles, environment variables, or deploy paths.

Steps

  1. List the real commands from package scripts, Makefiles, CI, or docs.
  2. Add the normal verification command sequence.
  3. Call out commands that require special profiles or credentials.
  4. Label commands that are expensive, destructive, or deploy production.
  5. Run the reviewer to catch missing or vague command sections.

Example review focus

CLAUDE.md excerpt
# CLAUDE.md

This repo is a React app. Use TypeScript and do not break anything.

## Style
Follow existing patterns.
What to fix
Add a Commands section: dev server, lint, test, build, deploy trigger, and any required environment variables. Replace `do not break anything` with a concrete verification gate such as `npm run lint && npm run test && npm run build` before final when relevant.

Common mistakes

  • Do not invent commands that are not in the repo.
  • Do not hide deploy commands inside prose.
  • Do not omit environment profiles, SSO, or credentials that affect verification.

FAQ

What commands should every CLAUDE.md include?
At minimum: install, dev, lint, test, typecheck if separate, build, and deploy or release notes if the repo has them.
Should production deploy commands go in CLAUDE.md?
Yes, but label them clearly and include any approval, branch, or profile constraints so the agent does not run them casually.
Can the reviewer find missing commands automatically?
It can flag missing sections and likely gaps, but you should still compare the output with the actual repo scripts and CI config.

Related CLAUDE.md guides

Review CLAUDE.md for Token Waste

Find vague, repeated, or unused CLAUDE.md instructions that cost tokens every Claude Code turn without improving behavior.

CLAUDE.md Repo Boundaries and Rules

Write CLAUDE.md rules that tell agents which files to edit, which files to avoid, and how to handle dirty worktrees safely.

Review CLAUDE.md Before Converting to AGENTS.md

Clean a CLAUDE.md first, then convert it into AGENTS.md, Cursor rules, GitHub Copilot instructions, or Windsurf rules.