npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

pi-agentsmd

v0.2.1

Published

Generate AGENTS.md contributor guides for Pi repositories.

Readme

pi-agentsmd

Teach Pi and other coding agents how your repository works with one command.

pi-agentsmd analyzes your project and creates a tailored AGENTS.md with the commands, conventions, and contribution guidance agents need to make better changes from their first turn.

Features

  • One-command repository onboarding — run /init to generate guidance at the repository root.
  • Project-aware instructions — the active model studies your structure, tooling, tests, and conventions instead of producing a generic template.
  • Safe regeneration — existing guidance stays untouched unless you explicitly pass --force.
  • Proven foundation — generation prompt is adapted from OpenAI Codex (Apache 2.0).

Installation

Install from npm:

pi install npm:pi-agentsmd

Install project-locally:

pi install -l npm:pi-agentsmd

During local development from this monorepo:

pi install /path/to/pi-mono/packages/pi-agentsmd

Usage

Generate AGENTS.md

Run the /init command inside a repository:

/init

Pi will inspect executable configuration and repository documentation, then include only verified guidance that is useful for the project. This can cover:

  • Non-obvious structure and package boundaries
  • Exact build, test, lint, and type-check commands
  • Focused verification steps and prerequisites
  • Generated or protected files
  • Conventions not enforced by tooling
  • Repository-specific security and completion criteria

The generated file refers to authoritative project documents instead of duplicating them. The model is instructed not to run project commands or install dependencies during generation.

Update existing AGENTS.md

If AGENTS.md already exists, use --force to reconcile it:

/init --force

Force mode preserves accurate project guidance while correcting stale or duplicate information.

How it works

The /init command sends a structured prompt to the active AI model. The model uses its file tools to inspect the repository and generate an AGENTS.md file tailored to the project. The package itself does not write the file — it delegates entirely to the model.

Development

Requirements:

  • Node.js >= 22.19.0
  • npm
npm install
npm run check
npm run pack:dry-run

Contributing

Contributions are welcome. See CONTRIBUTING.md for development workflow and pull request guidelines.

License

MIT. See LICENSE.

Includes a prompt derived from OpenAI Codex, licensed under the Apache License 2.0. See THIRD-PARTY-NOTICES.