agentleFS
Sign inStart free
vigneshm1995personalvigneshm1995personal/skillgate/AGENTS.md

skillgate

AGENTS.md1 starsChanged 32 days agoApache-2.0View on GitHub

Local Apache-2.0 gate for Agent Skills. One pack on disk + skillgate check (exit 0/1). No account. PyPI package: skillgate-ai. Hosted product lives in the private skillgate-ai repo. Docker: docker build -t skillgate:test --target runtime . then docker run --rm -v "$PWD/skills/pdf:/pack" skillgate:test. Always apply the skills in .cursor/skills: plan-mode, clean-coder, test-driven-vibe, frontend-design (UI), error-driven-debugger (bugs). Run tests locally and push only when green.

  • Installs packages

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Always apply the skills in .cursor/skills: plan-mode, clean-coder, test-driven-vibe, frontend-design (UI), error-driven-debugger (bugs).

    line 35

≈ “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 — skillgate (OSS)

Local Apache-2.0 gate for Agent Skills. One pack on disk + skillgate check (exit 0/1). No account. PyPI package: skillgate-ai. Hosted product lives in the private skillgate-ai repo.

Stack

  • Python ≥ 3.11 (src/skillgate_ai/), CLI via Typer (skillgate / skillgate-ai)
  • Optional local UI: skillgate ui (stdlib server + static assets under src/skillgate_ai/local_ui/)
  • Docker image ENTRYPOINT is skillgate; default CMD is check /pack

Layout

  • src/skillgate_ai/ — package (CLI, gate, judges, local UI, sync/helper)
  • tests/ — pytest
  • skills/ — seed packs (pdf, pdf-sabotaged)
  • docs/ — quickstart, pack schema, plans
  • scripts/ — maintainer helpers
  • .github/workflows/gate.yml — CI

Commands (from repo root)

python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest -q
skillgate check skills/pdf
skillgate check skills/pdf-sabotaged --expect-fail
ruff check .    # optional; ruff is a dev dep

Docker: docker build -t skillgate:test --target runtime . then docker run --rm -v "$PWD/skills/pdf:/pack" skillgate:test.

Agent skills

Always apply the skills in .cursor/skills: plan-mode, clean-coder, test-driven-vibe, frontend-design (UI), error-driven-debugger (bugs). Run tests locally and push only when green.

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