agentleFS
Sign inStart free
ahilles107ahilles107/gravity/AGENTS.md

gravity

AGENTS.md22 starsChanged 43 days agoMITView on GitHub

- Use GitHub Issues in this repository for all Gravity work, including internal maintainer tasks, bugs, plans, and follow-ups. Do not create or update Linear issues for Gravity. This overrides shared agent guidance that requires Linear or USE-XXX identifiers. - Use gh issue list, gh issue view, and gh issue create to find or track work. Reuse a relevant issue instead of creating duplicates. - Reference GitHub issue numbers (#123) in plans and pull requests. Use Fixes #123 only when…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository6 other files it gives its agents.

The file

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

11 rules. About 0 are common, 4 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use GitHub Issues in this repository for all Gravity work, including internal maintainer tasks, bugs, plans, and follow-ups.

    line 5
  2. Very specific:

    Use gh issue list, gh issue view, and gh issue create to find or track work.

    line 9
  3. Very specific:

    Keep credentials, private paths, account details, and private project data out of public issues.

    line 13
  4. Very specific:

    Read CONTRIBUTING.md. Outline a brief plan for non-trivial changes, then implement authorized work without repeated permission requests.

    line 20
  5. Very specific:

    Use pnpm and run pnpm run verify before considering work complete.

    line 22
  6. Distinctive:

    Never bypass hooks or branch protections.

    line 26
  7. Very specific:

    Keep changes concise and preserve strict TypeScript checks.

    line 31
  8. Distinctive:

    Use static imports, braces for control flow, explicit return types for exported functions, and readonly types where mutation is unnecessary.

    line 33
  9. Distinctive:

    Prefer shared code over duplication.

    line 35
  10. Distinctive:

    Use conventional commits with concise imperative subjects.

    line 36
  11. Very specific:

    Keep communication brief. Include file_path:line_number when referencing code.

    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

Gravity agent instructions

Issue tracking

  • Use GitHub Issues in this repository for all Gravity work, including internal maintainer tasks, bugs, plans, and follow-ups. Do not create or update Linear issues for Gravity. This overrides shared agent guidance that requires Linear or USE-XXX identifiers.
  • Use gh issue list, gh issue view, and gh issue create to find or track work. Reuse a relevant issue instead of creating duplicates.
  • Reference GitHub issue numbers (#123) in plans and pull requests. Use Fixes #123 only when merging the PR completes that issue.
  • Keep credentials, private paths, account details, and private project data out of public issues. Follow SECURITY.md for vulnerability reports. Do not copy an old private backlog into public issues without reviewing it for disclosure and confirming the migration scope.

Workflow

  • Read CONTRIBUTING.md. Outline a brief plan for non-trivial changes, then implement authorized work without repeated permission requests.
  • Use pnpm and run pnpm run verify before considering work complete. Report any unavailable checks; use hosted visual CI if local Docker is unavailable.
  • Preserve existing edits. Ask before deleting files, discarding changes, rewriting history, force-pushing, or applying irreversible migrations.
  • Never bypass hooks or branch protections. Release publication requires authorization; a code or documentation change alone does not authorize it.

Code and pull requests

  • Keep changes concise and preserve strict TypeScript checks. No any, unchecked type assertions, or non-null assertions. Narrow unknown inputs.
  • Use static imports, braces for control flow, explicit return types for exported functions, and readonly types where mutation is unnecessary.
  • Prefer shared code over duplication.
  • Use conventional commits with concise imperative subjects.
  • Target main. PR descriptions must have What, Why, and How tested sections, reference the relevant GitHub issue, and state rollout requirements and validation limitations.
  • Keep communication brief. Include file_path:line_number when referencing code. Do not send announcements or third-party messages without authorization.

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