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

@tarmo-randma/pi-superpowers-adapter

v0.1.3

Published

Minimal Pi adapter for upstream obra/superpowers skills.

Downloads

120

Readme

pi-superpowers-adapter

npm version

A small Pi package that gives Pi the upstream obra/superpowers skills without copying them into this repository.

Status: v0.1.3 release. Tested with Pi 0.75.x. Uses upstream Superpowers v5.1.0. Adds Pi startup guidance and a skill tool, but does not provide or replace a subagent extension.

Install

Ask your agent to run this:

Install this Pi package: pi install npm:@tarmo-randma/[email protected]

Local checkout

If you are installing from a local clone instead of GitHub:

pi install /path/to/pi-superpowers-adapter

Upstream version

To change the upstream Superpowers version, edit the obra-superpowers dependency in package.json, then update/reinstall the Pi package.

Example:

"obra-superpowers": "https://github.com/obra/superpowers/archive/refs/tags/v5.1.0.tar.gz"

Optional model tier config

Superpowers sometimes talks about Claude model tiers:

  • haiku = cheap/fast
  • sonnet = normal/default
  • opus = heavy/strong

Pi does not have these tiers built in. By default, the adapter tells agents to use normal Pi model behavior.

If you want explicit mappings, create one of these files:

~/.pi/agent/superpowers-adapter.json
.pi/superpowers-adapter.json

The user-level path follows Pi's active agent config directory. If Pi is started with PI_CODING_AGENT_DIR, the adapter reads superpowers-adapter.json from that directory instead of ~/.pi/agent.

Project config overrides user config.

{
  "models": {
    "cheap": "openai-codex/gpt-5.5",
    "default": "openai-codex/gpt-5.5",
    "heavy": "openai-codex/gpt-5.5"
  },
  "reasoning": {
    "cheap": "low",
    "default": "medium",
    "heavy": "high"
  }
}

Use exact Pi model IDs. To see the models available to Pi, run:

pi --list-models

Use the full provider/model-id form, for example openai-codex/gpt-5.5.

Reasoning values are Pi thinking levels: off, minimal, low, medium, high, or xhigh.

You can configure a model, a reasoning level, or both for each tier:

  • model only: use that model with its normal/default reasoning
  • reasoning only: use the currently active Pi model with that reasoning level
  • both: use that model with that reasoning level

Invalid tiers are ignored. For example, if a configured model is unavailable, or a configured reasoning level is not supported by the chosen model, the adapter gives no guidance for that tier.

Development

npm install
npm run typecheck