agentleFS
Sign inStart free
pulorepulore/claude-code-codex-config/AGENTS.md

claude-code-codex-config

AGENTS.md0 starsChanged 12 days agoApache-2.0View on GitHub

Instructions for every coding agent in this repo. Codex reads this file directly, and Claude Code reads it through CLAUDE.md. Codex doesn't expand imports, so every rule is written out here in full. Before you say a change is done, run the lint, the type-check and the tests that cover it, and say which ones you ran.

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

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

6 rules. About 1 is common, 4 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    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 one file: npm test -- src/orders/total.test.ts

    line 10
  2. Distinctive:

    Before you say a change is done, run the lint, the type-check and the tests that cover it, and say which ones you ran.

    line 14
  3. Distinctive:

    Keep each change to one concern.

    line 22
  4. Distinctive:

    Commit messages start with a short imperative subject, such as "Add retries to the webhook sender", followed by a body that says why.

    line 23
  5. Common:

    Never print, log or commit secrets, tokens or customer data.

    line 28
  6. Distinctive:

    Don't push, publish or open pull requests unless the user asks.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

AGENTS.md

Instructions for every coding agent in this repo. Codex reads this file directly, and Claude Code reads it through CLAUDE.md. Codex doesn't expand imports, so every rule is written out here in full.

Commands

  • Install: npm ci
  • Build: npm run build
  • Test everything: npm test
  • Test one file: npm test -- src/orders/total.test.ts
  • Lint: npm run lint, or npm run lint -- --fix to fix what it can
  • Type-check: npm run typecheck

Before you say a change is done, run the lint, the type-check and the tests that cover it, and say which ones you ran.

Conventions

  • npm is the package manager. Don't add a pnpm or yarn lockfile. Commit changes to package-lock.json with the change that caused them.
  • TypeScript in strict mode. Don't use any. If you can't avoid it, add a comment that says why.
  • Code lives in src/. Each test sits next to the file it tests, named <name>.test.ts.
  • File names are kebab-case.
  • Keep each change to one concern. Don't reformat or rename code you weren't asked to touch.
  • Commit messages start with a short imperative subject, such as "Add retries to the webhook sender", followed by a body that says why.

Secrets

  • Secrets live in .env files, and agents can't read them in this repo. If you need a value, ask the user. Never guess one or hard-code it.
  • Never print, log or commit secrets, tokens or customer data.
  • The dev server reads .env, so it won't start inside an agent's sandbox. Ask the user to start it.

Agent config

  • AGENTS.md, CLAUDE.md, .claude/, .codex/, .agents/ and .mcp.json control how agents work in this repo. Change them only when the user asks, and say what you changed.
  • Rules for every agent go in this file. Notes for Claude Code alone go in CLAUDE.md, below the import.
  • Don't push, publish or open pull requests unless the user asks.

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.

Check your setup, free