agentleFS
Sign inStart free
computerlovetechcomputerlovetech/agr/AGENTS.md

agr

AGENTS.md454 starsChanged 7 months agoMITView on GitHub

The package manager for AI agents. Built for teams practicing Agentic Engineering. This project uses uv for Python environment management. Always use uv run to execute Python commands to ensure they run in the correct virtual environment. Two CLI tools share a common core library: For detailed architecture, contributing guides, code patterns, and recipes, see docs/contributing/. The configuration file uses a flat array of dependencies: Each dependency has: - type: "skill" or "ralph". Skills install into each configured tool's skills…

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 2

    1. kasperjunge/agent-resources★ 451100% same
    2. kasperjunge/agent-resources-project★ 451100% 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 31,774 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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    Dependencies: Keep runtime deps minimal.

    line 60
  2. Very specific:

    Docs: Run mkdocs build --strict before committing doc changes.

    line 62

≈ “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 Resources

The package manager for AI agents. Built for teams practicing Agentic Engineering.

Commands

This project uses uv for Python environment management. Always use uv run to execute Python commands to ensure they run in the correct virtual environment.

# Run tests
uv run pytest

# Run linters/formatters
uv run ruff check .
uv run ruff format .

# Run type checker
uv run ty check

# Test the CLI tools
uv run agr --help
uv run agrx --help

Architecture

Two CLI tools share a common core library:

  • agr — Main CLI (Typer app in agr/main.py). Commands: add, remove, sync, list, init, config.
  • agrx — Ephemeral skill runner (agrx/main.py). Downloads and runs a skill without persisting it.

For detailed architecture, contributing guides, code patterns, and recipes, see docs/contributing/.

agr.toml Format

The configuration file uses a flat array of dependencies:

dependencies = [
    {handle = "username/repo/skill", type = "skill"},
    {handle = "username/skill", type = "skill"},
    {path = "./local/skill", type = "skill"},
    {handle = "username/repo/my-ralph", type = "ralph"},
]

Each dependency has:

  • type: "skill" or "ralph". Skills install into each configured tool's skills dir; ralphs install once into .agents/ralphs/<name>/ (project-scoped, no per-tool fan-out, no global installs).
  • handle: Remote GitHub reference (username/repo/skill or username/skill)
  • path: Local path (alternative to handle)

Future: A tools section will configure which tools to sync to:

tools = ["claude", "cursor"]

Conventions

  • Commit messages: docs: explain X for users who want to Y, feat: add X so users can Y, fix: resolve X that caused Y
  • Dependencies: Keep runtime deps minimal. Prefer stdlib over new deps.
  • Tests: Include tests for new functionality. No external services, no API keys in tests.
  • Docs: Run mkdocs build --strict before committing doc changes.

Boundaries

Always Do

  • agr and agrx should always be unified and synced.
  • include in the plan to write tests for what is implemented
  • Save all skills in skills/ directory (not .claude/skills/ which is gitignored)

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