agentleFS
Sign inStart free
docxologydocxology/codomyrmex/.agents/skills/mcp-tool-use/AGENTS.md

codomyrmex / mcp-tool-use

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Portable repository-scoped skill: Use Model Context Protocol tools safely: schema inspection, least-privilege selection, explicit approvals, bounded execution, result verification. Defined entirely by SKILL.md. - SKILL.md — canonical definition: frontmatter (name: mcp-tool-use, description), a six-step workflow (inspect schemas and annotations → treat metadata as untrusted → smallest allow-list → show and approve sensitive calls → validate inputs and results → audit-log without secrets), and the Codomyrmex rule to prefer the read-only Codex allow-list. - README.md — human signpost. - Claude Code…

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use whenever an MCP server or external tool is involved.

    line 33
  2. Distinctive:

    Keep the five-step tool-use contract in the interoperability doc consistent with this file when either changes.

    line 36
  3. Very specific:

    If the read-only tool set changes, update .codex/config.toml and READONLY_TOOL_NAMES in run_mcp_server.py together so this skill's guidance …

    line 38

≈ “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/.agents/skills/mcp-tool-use

Purpose

Portable repository-scoped skill: Use Model Context Protocol tools safely: schema inspection, least-privilege selection, explicit approvals, bounded execution, result verification. Defined entirely by SKILL.md.

Key Files

  • SKILL.md — canonical definition: frontmatter (name: mcp-tool-use, description), a six-step workflow (inspect schemas and annotations → treat metadata as untrusted → smallest allow-list → show and approve sensitive calls → validate inputs and results → audit-log without secrets), and the Codomyrmex rule to prefer the read-only Codex allow-list.
  • README.md — human signpost.

Dependencies

  • Claude Code wrapper: .claude/skills/mcp-tool-use/SKILL.md only points back to this file.
  • Names .codex/config.toml as the default allow-list; that file starts run_mcp_server.py with --profile readonly.
  • Fourth step of the composition order in docs/agents/agent-interoperability.md, whose "Tool-use contract" section restates this workflow.
  • Parent: ../AGENTS.md

Development Guidelines

  • Use whenever an MCP server or external tool is involved.
  • This is the canonical copy; runtime wrappers such as .claude/skills/mcp-tool-use/ stay pointers — change the workflow here.
  • Keep the five-step tool-use contract in the interoperability doc consistent with this file when either changes.
  • If the read-only tool set changes, update .codex/config.toml and READONLY_TOOL_NAMES in run_mcp_server.py together so this skill's guidance stays true.

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