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

@debangsu__/create-pr-review-agent

v1.0.4

Published

One-command installer for an AI PR review agent (GitHub Action) - drops a working, LLM-powered PR reviewer into any repo.

Readme

AI PR Review Agent

Automatic, AI-powered code review on every pull request. Install it once, give it an API key, and it reviews every PR from then on - no further setup, no config files to edit, no scripts to understand.

What it does

When someone opens or updates a pull request, this agent:

  1. Reads the diff
  2. Reviews each changed file with an LLM (Claude or GPT - your choice)
  3. Posts one comment on the PR summarizing what it found, sorted by severity (blocking issues first)

That's it. It runs as a GitHub Action - no server to host, no webhook to configure.

Install (2 minutes)

From inside your repo, run: npx @debangsu__/create-pr-review-agent

It will ask you two things:

  1. Which LLM to use - Anthropic (Claude) or OpenAI (GPT). Pick whichever one you have an API key for.
  2. Your API key - pasted once, sent straight to GitHub's secret store. Never written to a file, never logged.

If you have the GitHub CLI installed and logged in (gh auth login), the installer sets the secret for you automatically. If not, it prints 4 lines telling you exactly where to paste it on GitHub.com.

Then run: git push

Open a pull request. The agent reviews it automatically.

What the review looks like

A single comment on your PR summarizing what was found in each changed file, sorted with blocking issues first, then warnings, then info-level notes.

Requirements

  • A GitHub repository
  • An API key from Anthropic (console.anthropic.com) or OpenAI (platform.openai.com)
  • Node.js 18+ (only needed to run the installer once)

Known limitations (v1)

  • No cross-file context - each file is reviewed independently.
  • Per-PR file cap - by default only the first 30 changed files are reviewed, to keep cost and runtime bounded.
  • One comment per push, not inline line-comments (yet).

Cost

Every reviewed file is one LLM API call, billed by your own Anthropic/OpenAI account - this tool adds no markup.

Uninstalling

Delete .github/workflows/pr-review.yml and the scripts/ directory it added, then remove the API key secret from your repo settings.

Questions or issues

This is a young project - if something doesn't work the way this README says, please report it.