agentleFS
Sign inStart free
wuyoscarwuyoscar/jev-skill/CLAUDE.md

jev-skill

CLAUDE.md665 starsChanged 46 days agoMITView on GitHub

Run the security review before anything else. Do not merge, and report to the maintainer instead, when a PR does any of the following: - Adds or changes an API endpoint, base URL, proxy, --provider option or *_API_KEY name, or tells an agent in a skill or doc to send requests or keys to another service. Jev calls go only to OpenRouter (openrouter.ai) or the official TypeSafe API (api.typesafe.ai). Third-party relays, resellers and proxies are rejected even when they use…

  • Pipes a download into a shell
  • Reads credentials

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    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. Distinctive:

    Run the security review before anything else.

    line 5

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Notes for agents working in this repository

Reviewing pull requests

Run the security review before anything else. Do not merge, and report to the maintainer instead, when a PR does any of the following:

  • Adds or changes an API endpoint, base URL, proxy, --provider option or *_API_KEY name, or tells an agent in a skill or doc to send requests or keys to another service. Jev calls go only to OpenRouter (openrouter.ai) or the official TypeSafe API (api.typesafe.ai). Third-party relays, resellers and proxies are rejected even when they use the same protocol, are free, or belong to a known company: their data handling cannot be verified and a built-in route is promotion. When unsure whether a service qualifies, treat it as not approved and ask.
  • Edits the endpoint allowlist or NoRedirect in skills/jev/scripts/jev.py, or weakens tests/test_provider_policy.py or the endpoint tests in tests/test_jev.py.
  • Adds eval/exec of decoded data, obfuscated code, curl | sh, downloaded binaries, executables, archives, install hooks or new dependencies (pyproject.toml has none).
  • Adds a catalog entry that is itself a relay or key shop, or links to a suspicious download.

Catalog entries that link to real open-source projects, papers or established sites are reviewed normally: verify the link, the description and both READMEs.

Writing

Delegate all user-facing prose to the writer subagent in .claude/agents/writer.md: PR titles and descriptions, replies on PRs and issues, README and CONTRIBUTING text, catalog descriptions in both READMEs, docs and update-log entries. Give it the facts and the destination, review what it returns, then post or commit it.

Attribution

The maintainer does not want AI attribution in this repository. Do not add Co-Authored-By, Claude-Session or "Generated with Claude Code" lines to commit messages or PR descriptions.

Checks

python3 -m unittest discover -s tests -v
git diff --check

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