agentleFS
devhat-pmdevhat-pm/Claude-Playbook/templates/CLAUDE.md

Claude-Playbook / templates

CLAUDE.md1 starsChanged 28 days agoMITView on GitHub

Onboarding notes for Claude Code. Keep this short; Claude reads the code itself.

  • Reads credentials
  • Deletes or force-pushes
  • Commits and pushes

The file

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Test: pnpm test (run pnpm test -- --watch while iterating)

    line 11
  2. Distinctive:

    Commit messages: Conventional Commits.

    line 19
  3. Distinctive:

    Don't push to main; open a PR.

    line 26
  4. Distinctive:

    Don't delete or weaken tests to make them pass — tell me if a test is wrong.

    line 27
  5. Very specific:

    Don't run git push --force, rm -rf, or anything visible to others without asking.

    line 28
  6. Distinctive:

    Only change what's asked. No new abstractions, no defensive code for impossible cases, no docstrings on untouched code.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md — <project name>

Onboarding notes for Claude Code. Keep this short; Claude reads the code itself.

What this is

One paragraph: what the project does, who uses it, the main entry points.

Commands

  • Install: pnpm install
  • Dev: pnpm dev
  • Test: pnpm test (run pnpm test -- --watch while iterating)
  • Lint/format: pnpm lint && pnpm format
  • DB migrations: pnpm db:push — never hand-edit SQL in migrations/

Conventions that differ from defaults

  • TypeScript strict; no any without a comment.
  • Server code lives in apps/api, UI in apps/web; shared types in packages/types.
  • Errors: throw AppError subclasses; never swallow.
  • Commit messages: Conventional Commits.

Gotchas

  • .env.local is required; copy from .env.example.
  • Tests hit a local Postgres on port 5433, not 5432.

Never

  • Don't push to main; open a PR.
  • Don't delete or weaken tests to make them pass — tell me if a test is wrong.
  • Don't run git push --force, rm -rf, or anything visible to others without asking.

Scope

Only change what's asked. No new abstractions, no defensive code for impossible cases, no docstrings on untouched code.

See also

@docs/architecture.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.