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

@ai-squad/cli

v0.7.2

Published

ai-squad CLI — deploy SDD/Discovery squads. Skills+agents user-global (~/.claude/), hooks per-repo (<repo>/.claude/hooks/) to keep agentops telemetry consistent with hook version.

Readme

@ai-squad/cli

CLI to deploy ai-squad squads into Claude Code. Skills + agents install user-globally; hooks install per-repo (so the .agent-session/ telemetry your @ai-squad/agentops reports rely on stays consistent with the hook version that produced it).

Install

npm i -g @ai-squad/cli

Usage

# Run once per consumer repo — installs skills+agents globally AND hooks locally.
cd <consumer-repo>
ai-squad deploy

# Selective:
ai-squad deploy --squad sdd          # only the sdd squad
ai-squad deploy --hooks-only         # re-sync just hooks (after upgrading the CLI)
ai-squad deploy --global-only        # skip per-repo hooks (CI / dotfile flow)
ai-squad deploy --cursor             # also mirror to ~/.cursor/
ai-squad help

After deploy:

  • Skills land flat in ~/.claude/skills/<skill>/ (user-global)
  • Subagents in ~/.claude/agents/<agent>.md (user-global)
  • Python hooks in <repo>/.claude/hooks/<name>.py (per-repo, chmod +x)
  • .claude/hooks/ is appended to the repo's .gitignore automatically

Hook scripts are referenced from component frontmatter as python3 $CLAUDE_PROJECT_DIR/.claude/hooks/<name>.py — Claude Code expands $CLAUDE_PROJECT_DIR to the current project root before invoking the hook.

Why per-repo hooks?

  • Telemetry consistency: the hooks that produced .agent-session/<id>/dispatch-manifest.json ship in the same repo, so the report engine and the data always agree on schema.
  • Reproducible CI: runners don't need a pre-seeded $HOMEai-squad deploy in setup works.
  • Multi-version safe: different consumer repos can run different ai-squad versions concurrently without ~/.claude/hooks/ collisions.
  • Inspectable: cat <repo>/.claude/hooks/verify-tier-calibration.py shows exactly what is running, no guessing about which ~/.claude/ version got installed.

Upgrading

npm i -g @ai-squad/cli@latest
cd <each consumer repo>
ai-squad deploy --hooks-only    # pick up the new hooks

The global skills+agents update automatically on any ai-squad deploy.

Squads bundled

  • sdd — Spec-Driven Development pipeline (4 phases: Specify → Plan → Tasks → Implementation). Subagents: dev, code-reviewer, logic-reviewer, qa, blocker-specialist, audit-agent.
  • discovery — Cagan-style Discovery (Frame → Investigate → Synthesize). Subagents: codebase-mapper, risk-analyst.

Companion: observability

For session reports (tokens, cost, AC closure, reviewer findings):

npx @ai-squad/agentops report

Requirements

  • Node ≥ 18
  • Python 3.8+ on PATH (hook scripts are pure-stdlib Python)

License

MIT — Gabriel Andrade