agentleFS
cisagovcisagov/ScubaGoggles/AGENTS.md

ScubaGoggles

AGENTS.md408 starsChanged 5 months agoCC0-1.0View on GitHub

Instructions for AI coding agents working in this repository. Maintainers need to be able to tell at a glance when a coding agent contributed to a change. If you are a coding agent, you MUST disclose that in every commit you create and in every pull request you open, regardless of how small the change is. The human developer who directed you remains the author and is responsible for the change. Attribution supplements that; it does not replace it. Add…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. cisagov/ScubaGear★ 2.8k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • 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 33,315 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 repositoryOne other file it gives its agents.

The file

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

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Add a Co-authored-by trailer to every commit message, naming the agent that produced the change.

    line 13
  2. Distinctive:

    Use the identity that matches the agent you are:

    line 21
  3. Distinctive:

    Always name the specific agent.

    line 34
  4. Distinctive:

    Keep one trailer per agent.

    line 35
  5. Distinctive:

    Do not remove or rewrite existing trailers when amending or rebasing.

    line 36
  6. Distinctive:

    Do not add the human developer's name as an agent, and do not impersonate a human.

    line 37
  7. Distinctive:

    Every PR description must include an attribution line stating which agent was used.

    line 41
  8. Distinctive:

    If the agent wrote or substantially edited the PR description itself, say so.

    line 51
  9. Distinctive:

    Keep the attribution when the description is edited later.

    line 52
  10. Distinctive:

    If a PR contains a mix of human-written and agent-written commits, still include the attribution line.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Instructions for AI coding agents working in this repository.

Attribution requirements

Maintainers need to be able to tell at a glance when a coding agent contributed to a change. If you are a coding agent, you MUST disclose that in every commit you create and in every pull request you open, regardless of how small the change is.

The human developer who directed you remains the author and is responsible for the change. Attribution supplements that; it does not replace it.

Commits

Add a Co-authored-by trailer to every commit message, naming the agent that produced the change. The trailer goes at the end of the message, separated from the body by a blank line.

Fix off-by-one error in pagination

Co-authored-by: <Agent Name> <agent-email@example.com>

Use the identity that matches the agent you are:

AgentTrailer
Claude / Claude CodeCo-authored-by: Claude <noreply@anthropic.com>
OpenAI CodexCo-authored-by: Codex <noreply@openai.com>
GitHub CopilotCo-authored-by: Copilot <noreply@github.com>
CursorCo-authored-by: Cursor Agent <cursoragent@cursor.com>
Gemini CLICo-authored-by: Gemini <noreply@google.com>
Any other agentCo-authored-by: <Agent Name> <noreply@<vendor-domain>>

Rules:

  • Always name the specific agent. Never use a vague label such as "AI" or "bot".
  • Keep one trailer per agent. If several agents contributed, add one trailer for each.
  • Do not remove or rewrite existing trailers when amending or rebasing.
  • Do not add the human developer's name as an agent, and do not impersonate a human.

Pull request descriptions

Every PR description must include an attribution line stating which agent was used. Put it in its own section at the bottom of the description:

---
🤖 This pull request was created with the assistance of <Agent Name> (<model, if known>), directed by @<github-username>.

Rules:

  • Name the agent and, when you know it, the model or version used.
  • If the agent wrote or substantially edited the PR description itself, say so.
  • Keep the attribution when the description is edited later. Do not delete it.
  • If a PR contains a mix of human-written and agent-written commits, still include the attribution line.

Checklist before committing or opening a PR

  1. Does every commit you contributed to include the correct Co-authored-by trailer?
  2. Does the PR description include the attribution section naming your agent?
  3. Is the attribution accurate, with no overstating or understating of what the agent did?

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.