agentleFS
Sign inStart free
Sanix-DarkerSanix-Darker/git-ci-skills/AGENTS.md

git-ci-skills

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

This public repository contains portable Agent Skills and bootstrap helpers for connecting AI agents to a GCI controller. - Keep product source in the private Sanix-Darker/git-ci repository. - Keep binaries and checksums in Sanix-Darker/git-ci.releases. - Never commit host defaults, private keys, passphrases, tokens, databases, logs, customer repository data, or generated client credentials. - Use the existing SSH agent and OpenSSH host verification. - Never add StrictHostKeyChecking=no or accept private key text as input. - Do not expose generic shell, SQL,…

  • 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 31,700 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

9 rules. About 2 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈2

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Keep product source in the private Sanix-Darker/git-ci repository.

    line 10
  2. Very specific:

    Keep binaries and checksums in Sanix-Darker/git-ci.releases.

    line 11
  3. Common:

    Never commit host defaults, private keys, passphrases, tokens, databases, logs, customer repository data, or generated client credentials.

    line 12
  4. Distinctive:

    Use the existing SSH agent and OpenSSH host verification.

    line 14
  5. Very specific:

    Never add StrictHostKeyChecking=no or accept private key text as input.

    line 15
  6. Common:

    Do not expose generic shell, SQL, filesystem, environment, or secret-read tools.

    line 16
  7. Distinctive:

    Keep scripts POSIX shell, small, auditable, and safe to rerun.

    line 17
  8. Very specific:

    Keep SKILL.md short. Put detailed contracts in references/.

    line 18
  9. Distinctive:

    Do not state that an MCP capability works until the corresponding released GCI binary and its contract/E2E tests exist.

    line 22

≈ “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

GCI skills repository contract

Purpose

This public repository contains portable Agent Skills and bootstrap helpers for connecting AI agents to a GCI controller.

Boundaries

  • Keep product source in the private Sanix-Darker/git-ci repository.
  • Keep binaries and checksums in Sanix-Darker/git-ci.releases.
  • Never commit host defaults, private keys, passphrases, tokens, databases, logs, customer repository data, or generated client credentials.
  • Use the existing SSH agent and OpenSSH host verification.
  • Never add StrictHostKeyChecking=no or accept private key text as input.
  • Do not expose generic shell, SQL, filesystem, environment, or secret-read tools.
  • Keep scripts POSIX shell, small, auditable, and safe to rerun.
  • Keep SKILL.md short. Put detailed contracts in references/.

Release rule

Do not state that an MCP capability works until the corresponding released GCI binary and its contract/E2E tests exist. Bootstrap scripts must fail closed when the remote binary does not advertise the required command.

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