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

leapfrog-agent

v0.1.2

Published

Bootstrap any project with Leapfrog's org-standard AI development setup

Downloads

307

Readme

leapfrog-agent

Bootstrap any project with Leapfrog's org-standard AI development setup — skills, a signal-matching router, and an adoption usage log.

Quick start

npx leapfrog-agent init        # bootstrap (interactive, offline)
npx leapfrog-agent add <skill> # install another bundled skill
npx leapfrog-agent update      # refresh router + preset skills
npx leapfrog-agent status      # health + adoption report
npx leapfrog-agent compress    # caveman-compress prose files (needs API key)

What init creates

  • CLAUDE.md — project index (yours to edit)
  • .ai/FRAMEWORK.md — skill router + usage-log rules (maintainer-owned)
  • .ai/skills/ — installed skills; mirrored to .agents/ and .pi/
  • MEMORY.md, .ai/CONTEXT.md, .ai/LEARNINGS.md
  • .leapfrog.json — config (committed, no secrets)
  • .env.schema — env var reference; put real keys in .env.local (gitignored)

Plugins (skills + MCP + hooks)

Skills are markdown instructions; plugins add hooks and MCP servers too (e.g. caveman, ponytail, claude-mem). Install the curated org set:

npx leapfrog-agent plugins list      # curated + installed
npx leapfrog-agent plugins add <name>
npx leapfrog-agent plugins sync      # all preset plugins
npx leapfrog-agent plugins status    # presence report

On Claude Code, install uses the native plugin system (claude plugin …). On Pi, leapfrog writes the hook + MCP config directly. Every change to a shared config file is shown as a diff and confirmed before writing. Plugin secrets are recorded as env-var names in .env.schema — set real values in .env.local (gitignored).

How skills get used

.ai/FRAMEWORK.md tells the agent to match task signals to a skill, confirm, and log each firing to .ai/usage.log. status reports which skills fire and which never do — so the org standard is driven by data.

Config

.leapfrog.json records your provider/model (by keyEnv name only — never the key), and two skill tiers: preset (refreshed by update) and custom (never touched).

Requirements

Node 20+. macOS/Linux (Windows: skills are copied instead of symlinked).