agentleFS
Badhon-00Badhon-00/MDCP/AGENTS.md

MDCP

AGENTS.md2 starsChanged 5 days agoMITView on GitHub

Use these instructions for Codex and other non-Claude agents. Preserve all existing Claude-specific files, manifests, skills, workflows, and documentation unless explicitly asked to change them. Inspect before editing. Never overwrite user work or secrets. Keep third-party skill licenses and notices intact. Add portable skills under .agents/skills/, ChatGPT material under .gpt/, and Codex material under .codex/. Add tests for behavior changes. Run python3 scripts/validate.py when possible and report exact results. Never claim unrun tests passed. Require explicit approval for destructive operations,…

The file

Files
AGENTS.md

MDCP Agent Instructions

Use these instructions for Codex and other non-Claude agents. Preserve all existing Claude-specific files, manifests, skills, workflows, and documentation unless explicitly asked to change them. Inspect before editing. Never overwrite user work or secrets. Keep third-party skill licenses and notices intact. Add portable skills under .agents/skills/, ChatGPT material under .gpt/, and Codex material under .codex/. Add tests for behavior changes. Run python3 scripts/validate.py when possible and report exact results. Never claim unrun tests passed. Require explicit approval for destructive operations, production deployments, database writes, permission changes, and active security scans.

LLM routing

For local and free-tier model routing, read integrations/omniroute/README.md and the omniroute-free-llm-routing skill. Use OmniRoute only when installed and configured. Never promise unlimited hosted inference, bypass provider quotas, or expose gateway/API keys. Claude Code and Codex CLI can use the upstream OmniRoute launch/configuration flow; Claude.ai and ChatGPT web chat cannot be transparently redirected by repository instructions alone.

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.