agentleFS
Sign inStart free
thientranhungthientranhung/astragentic/AGENTS.md

astragentic

AGENTS.md4 starsChanged 6 days agoApache-2.0View on GitHub

This file governs work on the harness repository. It does not assign a downstream Thomas or Builder role. Read docs/codex/README.md before changing Codex integration. - Preserve Claude Code behavior. Put Codex-specific contracts and configuration in separate files. Do not rewrite .claude/, CLAUDE.md, or Claude role adapters to accommodate Codex unless the owner explicitly expands scope. - Inspect the current tree and installed CLI before relying on historical integration notes. For every proposed capability, record a measurement and source; label untested…

  • 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 31,774 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

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not silently diverge them or disable the check to add Codex behavior.

    line 16
  2. Distinctive:

    Keep owner model, permission, trust, and orchestrator choices owner-controlled.

    line 17
  3. Distinctive:

    Do not edit user-level Codex configuration or switch active role assignments implicitly.

    line 18
  4. Distinctive:

    Test the changed integration at its real boundary.

    line 21
  5. Distinctive:

    Keep edits narrow; do not commit, publish, or deploy merely to finish integration work.

    line 23

≈ “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

Astragentic development in Codex

This file governs work on the harness repository. It does not assign a downstream Thomas or Builder role. Read docs/codex/README.md before changing Codex integration.

  • Preserve Claude Code behavior. Put Codex-specific contracts and configuration in separate files. Do not rewrite .claude/, CLAUDE.md, or Claude role adapters to accommodate Codex unless the owner explicitly expands scope.
  • Inspect the current tree and installed CLI before relying on historical integration notes. For every proposed capability, record a measurement and source; label untested runtime behavior not measured rather than treating documentation as execution proof.
  • Claude runtime documents are implementation research sources only. Codex role, agent, and skill instructions must be self-contained or reference Codex-owned contracts; never require loading a Claude role, adapter, or dispatch document.
  • The paired skill trees currently have an installer-enforced equality contract. Do not silently diverge them or disable the check to add Codex behavior.
  • Keep owner model, permission, trust, and orchestrator choices owner-controlled. Do not edit user-level Codex configuration or switch active role assignments implicitly.
  • A prompted check is not an enforced gate. Never manufacture Claude mod events, skill invocation receipts, review results, or completion markers for Codex sessions.
  • Test the changed integration at its real boundary. Report static checks, mocked checks, and live-session checks separately. Do not claim release readiness from syntax.
  • Keep edits narrow; do not commit, publish, or deploy merely to finish integration work.

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