agentleFS
Sign inStart free
docxologydocxology/codomyrmex/.codex/AGENTS.md

codomyrmex

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Project-scoped configuration for the Codex agent runtime. It registers the Codomyrmex MCP server for Codex with a read-only tool allow-list and prompt-before-use approvals. - config.toml — a single [mcp_servers.codomyrmex] table that starts scripts/model_context_protocol/run_mcp_server.py through uv run with --transport stdio --profile readonly, sets startup_timeout_sec = 20, tool_timeout_sec = 60, and default_tools_approval_mode = "prompt", and enables ten read-only tools (git_status, git_diff, read_file, list_directory, search_code, analyze_python_file, json_query, checksum_file, list_modules, get_module_info). - README.md — human signpost. - scripts/model_context_protocol/run_mcp_server.py is the server Codex launches; its…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Do not commit secrets or credentials into config.toml.

    line 34
  2. Distinctive:

    Treat edits as behavior changes for any Codex-driven agent sessions.

    line 36
  3. Very specific:

    Keep the checked-in surface read-only: add a write or command tool only for a named task and restore the allow-list afterwards.

    line 37
  4. Distinctive:

    Check what the server actually exposes before changing the allow-list:

    line 40

≈ “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 — codomyrmex/.codex

Purpose

Project-scoped configuration for the Codex agent runtime. It registers the Codomyrmex MCP server for Codex with a read-only tool allow-list and prompt-before-use approvals.

Key Files

  • config.toml — a single [mcp_servers.codomyrmex] table that starts scripts/model_context_protocol/run_mcp_server.py through uv run with --transport stdio --profile readonly, sets startup_timeout_sec = 20, tool_timeout_sec = 60, and default_tools_approval_mode = "prompt", and enables ten read-only tools (git_status, git_diff, read_file, list_directory, search_code, analyze_python_file, json_query, checksum_file, list_modules, get_module_info).
  • README.md — human signpost.

Dependencies

  • scripts/model_context_protocol/run_mcp_server.py is the server Codex launches; its READONLY_TOOL_NAMES set defines the readonly profile, so enabled_tools must stay a subset of it.
  • Codex discovers project skills from .agents/skills/; this file configures MCP only, and Codex applies it only to trusted projects.
  • Referenced by docs/agents/agent-interoperability.md, .agents/skills/mcp-tool-use/SKILL.md, and .agents/skills/agent-interop/SKILL.md.
  • Parent: ../README.md · Root contract: ../AGENTS.md

Development Guidelines

  • Do not commit secrets or credentials into config.toml; keep secrets in the runtime's own credential store.
  • Treat edits as behavior changes for any Codex-driven agent sessions.
  • Keep the checked-in surface read-only: add a write or command tool only for a named task and restore the allow-list afterwards; do not switch the checked-in server to --profile full.

  • Check what the server actually exposes before changing the allow-list:

    uv run python scripts/model_context_protocol/run_mcp_server.py --profile readonly --list-tools
codex mcp list

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