agentleFS
Sign inStart free
sam-mountainmansam-mountainman/codex-mcp/AGENTS.md

codex-mcp

AGENTS.md0 starsChanged 23 days agoMITView on GitHub

If a user asks an AI coding agent to set up this repository, complete the setup for Claude Code instead of stopping at a README summary. Do not hard-code the user's requested model or reasoning level into source. The server default is gpt-5.6-sol with max, while every model tool accepts per-call model and reasoning_effort overrides. Preserve explicit user choices exactly and let the local Codex CLI validate model availability.

  • 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 31,700 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 repositoryOne other file it gives its agents.

The file

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

5 rules. About 0 are common, 4 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a user asks an AI coding agent to set up this repository, complete the setup for Claude Code instead of stopping at a README summary.

    line 3
  2. Distinctive:

    Read the current default branch and release metadata when the repository is hosted remotely.

    line 5
  3. Distinctive:

    Before changing authentication, use a structured question UI when available.

    line 8
  4. Distinctive:

    Run the platform installer:

    line 12
  5. Very specific:

    Do not hard-code the user's requested model or reasoning level into source.

    line 19

≈ “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

codex-mcp setup contract

If a user asks an AI coding agent to set up this repository, complete the setup for Claude Code instead of stopping at a README summary.

  1. Read the current default branch and release metadata when the repository is hosted remotely. Do not choose a version from a stale local cache.
  2. Confirm Node.js 18+ is available.
  3. Install the official Codex CLI (@openai/codex) and Claude Code (@anthropic-ai/claude-code) only when missing.
  4. Before changing authentication, use a structured question UI when available. Present these choices in order:
    • ChatGPT account login (recommended): run codex login and use the user's ChatGPT/Codex allowance.
    • OpenAI API key: use metered OpenAI Platform billing and pass the key through stdin, never a command argument or normal chat.
    • Existing authentication: preserve a working codex login status session.
  5. Run the platform installer:
    • macOS/Linux: ./install.sh
    • Windows PowerShell: .\install.ps1
  6. Require npm run verify, claude plugin validate --strict ., and claude mcp list to succeed for plugin:codex-mcp:codex.
  7. Unless the user opts out, run npm run live-smoke. This makes two small model calls and verifies both a new session and continuation with a changed reasoning level.
  8. Tell the user to restart Claude Code or run /reload-plugins, then ask Codexの状態を確認して.

Do not hard-code the user's requested model or reasoning level into source. The server default is gpt-5.6-sol with max, while every model tool accepts per-call model and reasoning_effort overrides. Preserve explicit user choices exactly and let the local Codex CLI validate model availability.

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