agentleFS
vaaynevaayne/agent-kit/AGENTS.md

agent-kit

AGENTS.md54 starsChanged 27 days agoMITView on GitHub

_AGENTS.md is the shared instruction file this repo ships to every framework. It is not this file's job to restate it; read it directly when working on its content. Keep tokens, login state, transcripts, and machine-specific provider settings out of config/. Configuration sync uses copies, backs up changes, and refuses local edits to repository keys. Keys that only the target sets stay local. Review local edits before using --replace. mise run sync runs format first, so a sync can leave…

  • 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 31,843 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 repository10 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Keep tokens, login state, transcripts, and machine-specific provider settings out of config/.

    line 21

≈ “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

Agent Instructions

_AGENTS.md is the shared instruction file this repo ships to every framework. It is not this file's job to restate it; read it directly when working on its content.

Layout

  • skills/ — local skills, one directory per skill, plus remote-skills.txt
  • config/claude/, config/codex/, and config/pi/ — public agent configuration
  • .mise/tasks/sync/ — configuration, skill, and BB server sync tasks
  • scripts/sync_config.py — configuration deployment with backups and a baseline

Commands

  • mise run format — dprint across TS/JSON/YAML/TOML/Markdown/HTML and ruff for Python
  • mise run sync — format, copy configuration, link instructions, and sync skills to BB
  • mise run sync:skills — copy local and remote skills to BB_SKILLS_TARGET
  • mise run sync:config -- --check — check configuration without writing files
  • "$(mise which python3)" -m unittest discover -s tests -v — configuration and skill sync tests

Keep tokens, login state, transcripts, and machine-specific provider settings out of config/. Configuration sync uses copies, backs up changes, and refuses local edits to repository keys. Keys that only the target sets stay local. Review local edits before using --replace.

mise run sync runs format first, so a sync can leave formatting changes in the working tree. Commit them separately.

Code style

  • Python: 3.12+, ruff (88-char lines, double quotes), snake_case, type hints required
  • TypeScript: strict mode, camelCase functions, PascalCase types, Zod for validation

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.