agentleFS
Sign inStart free
isanchez-aguilarisanchez-aguilar/relayrace-ai/AGENTS.md

relayrace-ai

AGENTS.md0 starsChanged 11 days agoApache-2.0View on GitHub

Rules for any coding agent, or person, working in this repository.

  • Reads credentials
  • 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 repository4 other files it gives its agents.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Never read, print or store secrets: .env, .dev.vars, keys, tokens.

    line 7
  2. Distinctive:

    Never write permission allow-rules for any tool.

    line 8
  3. Very specific:

    No machine paths in code: everything optional comes from lib/config.mjs (config file, then RELAYRACE_* variables, with the old RELAYKIT_* …

    line 10
  4. Distinctive:

    Never use the Fable model without the owner's explicit approval for that use.

    line 13
  5. Very specific:

    Before pushing, run relayrace ci-local (or node --test).

    line 14

≈ “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 — Relayrace

Rules for any coding agent, or person, working in this repository.

  • Node built-ins only (no dependencies). Tests use node --test; the suite must pass on Windows, macOS and Linux (CI runs all three). Every change ships with its tests.
  • Code, comments, docs and commits in English.
  • Never read, print or store secrets: .env, .dev.vars, keys, tokens.
  • Never write permission allow-rules for any tool. Print them for the owner to apply.
  • init never overwrites existing files. sync only replaces files it generated; never run it without --check unless the owner asked.
  • No machine paths in code: everything optional comes from lib/config.mjs (config file, then RELAYRACE_* variables, with the old RELAYKIT_* and AI_KIT_* still read).
  • Files that init copies into other repos (agents/, skills/, templates/, prompts/, qwen.mjs) get no license header; the notice is LICENSE-TEMPLATES. qwen.mjs is installed with only lib/exe.mjs and lib/guardrails.mjs beside it (as scripts/lib/), so it may import nothing else from lib/.
  • One branch per change; never commit straight to main; sign commits off with git commit -s (DCO). No merge without the maintainer's OK.
  • Never use the Fable model without the owner's explicit approval for that use.
  • Before pushing, run relayrace ci-local (or node --test); relayrace ci-local --install-hook does it on every push.

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