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

pm-council

v0.1.0-alpha.1

Published

Install PM Council — five AI strategists that argue about your product decisions — into Cursor or Claude Code.

Downloads

111

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

raa2121raa2121

Keywords

claude-codecursorproduct-managementpmai-agentssubagentsmulti-agent-debateprdroadmapproduct-strategy

Readme

PM Council

Five AI strategists argue about your product decisions before you ship.

Status: v0.1 in build. Demo GIF and real transcript drop with the v0.1.0 release.

One command. Works in Claude Code and Cursor.

Install

Claude Code (native plugin):

/plugin marketplace add RyanAlberts/pm-council
/plugin install pm-council@RyanAlberts/pm-council

Cursor (one-line):

npx pm-council install

Fallback for either host:

curl -fsSL https://raw.githubusercontent.com/RyanAlberts/pm-council/main/install.sh | sh

See INSTALL.md for manual copy, user-scope vs project-scope, and troubleshooting.

Use it

/council What should we build next?
/council Should we kill the legacy plan tier to free roadmap capacity?
/council Build our own feature flags or integrate LaunchDarkly?

See docs/transcript-example.md for a full real run.

What you get

Five strategists, each carrying a domain sub-lens encoded in structured YAML output. Not a generic agent pool — each persona is prompt-engineered at a Principal-PM bar with explicit reasoning-rigor rules (calibrated confidence, falsifiable claims, cite-a-specific-frame, mandatory dissent).

| Strategist | Core lens | Sub-lens baked in | |---|---|---| | sounding-board | Frames the real trade-offs | UX — user archetype + Teresa Torres opportunity-solution tree | | pre-mortem | 12-month failure post-mortem | Economics + Engineering — failure modes tagged by dimension | | devils-advocate | Strongest case against | Legal — regulatory / IP / contract blockers as dissent vectors | | opportunity-cost | What you're not doing by doing this | — | | working-backwards | PRFAQ from the future | Marketing — ICP + competitor contrast + channel |

All five carry a shared strategy canon (Hamilton Helmer 7 Powers, Paul Graham startup lenses, Warren Buffett investor lenses, Elon Musk first-principles / the Algorithm) they can invoke by name.

Debate mechanics

Round 2 triggers when any rubric dimension has score spread ≥ 2 or verdicts split across strategists. In Round 2 each strategist sees the other four's outputs and revises — position changes must cite what changed their mind. Same shape as Du et al. Multi-Agent Debate (arXiv:2305.14325), deterministic trigger instead of a supervisor judgment.

The threshold was calibrated empirically — see docs/round-2-calibration.md for the methodology and the test decisions that tuned it.

What this is not

  • Not another awesome-list. Five adversarially calibrated personas beat 500 generic ones on directional product decisions.
  • Not CrewAI-for-PMs. CrewAI gives you the Lego bricks; pm-council is a pre-assembled debate machine where the scoring rubric — not a supervisor agent — decides when the model needs another round.
  • Not a founder framework. Built for PMs working on PRDs, roadmap trade-offs, build/buy, launch timing, and greenfield product questions. Different vocabulary.

License

MIT — see LICENSE.