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

autostackrc

v0.0.1

Published

Auto-detect your tech stack and generate tailored rules & commands for AI code assistants (Claude Code, Cursor, Copilot, opencode)

Readme

autostackrc

Detect your tech stack → generate tailored rules & commands for your AI code assistants.

autostackrc generates rules and slash-commands specific to your stack and writes them in the native format of each assistant — Claude Code, Cursor, GitHub Copilot, and opencode.

📖 Docs & portal: https://cesarzuniga.github.io/autostackrc (deployed via GitHub Pages from docs/).

npx autostackrc

How it works

  1. Detect — scans package.json, config files, and file extensions to identify your stack.
  2. Assemble — builds a baseline of rules + commands from static templates (offline, auditable).
  3. Enrich — hands the baseline to your installed AI coder CLI (using its existing login session, no API key) to make the rules specific and correct for your stack.
  4. Write — projects one agent-agnostic result into every selected assistant's files.

If no coder CLI is found (or --no-llm), it emits the static templates as-is — never hard-fails.

Output per assistant

| Assistant | Rules | Commands | | ------------- | ---------------------------------------------------------------- | ------------------------------- | | Claude Code | CLAUDE.md (managed block) | .claude/commands/*.md | | Cursor | .cursor/rules/*.mdc (one per tech, globs/alwaysApply) | .cursor/commands/*.md | | GitHub Copilot| .github/copilot-instructions.md + .github/instructions/*.md | .github/prompts/*.prompt.md | | opencode | AGENTS.md (managed block) | .opencode/command/*.md |

Shared files (CLAUDE.md, AGENTS.md, copilot-instructions.md) are edited inside an <!-- autostackrc:start -->…<!-- autostackrc:end --> block, so re-runs update only that block and leave your own content untouched. A autostackrc-lock.json records every file written.

Enrichment without an API key

autostackrc does not call any API directly. It detects an installed coder CLI in this order and runs it headless, feeding the prompt on stdin and parsing the JSON it returns:

  • claude (Claude Code) — claude -p
  • opencodeopencode run
  • cursor-agent (Cursor) — cursor-agent -p

Whatever session that CLI is already logged into is what does the work. Force one with --coder.

Options

npx autostackrc                        Detect, generate, write (interactive)
  -y, --yes         Skip confirmation prompts
  --dry-run         Show plan, write nothing
  -a, --agent       Target subset: claude-code cursor copilot opencode
  --no-llm          Skip enrichment, emit static templates only
  --coder <id>      Force coder CLI: claude, opencode, cursor-agent
  --model <id>      Model hint passed to the coder CLI (if supported)
  -v, --verbose     Show traces and error detail
  -h, --help        Show this help

Requirements

Node.js >= 22.6.0 (uses native TypeScript type-stripping).

Extending

  • Add a technology: create templates/rules/<id>.md (frontmatter + rule body) and add a seed (detect rules + command ids) to TECH_SEEDS in catalog.ts.
  • Add a command: create templates/commands/<id>.md (frontmatter + prompt body); mark it generic: true to emit for every stack, or wire its id into a tech's commands in catalog.ts.
  • Add an assistant: add a writer in writers/ and register it in writer.ts + agents.ts.