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

pi-model-presets

v0.1.0

Published

Named model and reasoning presets for Pi

Readme

pi-model-presets

Small model and reasoning presets for Pi.

Install

pi install npm:pi-model-presets

For development or a Git-based install:

pi install git:github.com/giuseppecrj/pi-model-presets

Restart Pi or run /reload, then use:

/preset
/preset explore
/preset plan
/preset orchestrate
/preset implement
/preset review

Defaults

| Preset | Model | Reasoning | Use | | --- | --- | --- | --- | | explore | openai-codex/gpt-5.3-codex-spark | low | Bounded repository reconnaissance | | plan | openai-codex/gpt-5.6-sol | high | Grilling, ADRs, specifications, tickets, and hard diagnosis | | orchestrate | openai-codex/gpt-5.6-sol | high | Lead a multi-step task; delegate independent work and integrate results | | implement | openai-codex/gpt-5.6-terra | medium | Routine implementation, TDD, validation, and documentation | | review | xai-auth/grok-4.5 | high | Independent and adversarial review |

A preset changes the active model and reasoning level, then appends its phase-specific instructions to the system prompt for later agent turns. Presets do not add or remove tools. Select another preset to replace the active phase context.

Configuration

Add or override presets in either location:

  • ~/.pi/agent/model-presets.json
  • <project>/.pi/model-presets.json

Project presets load only for trusted projects and override global presets with the same name. Same-name presets merge by field, so a configuration can override only the fields it needs. Set "instructions": "" to clear inherited instructions. A new preset must define provider, model, and thinkingLevel after merging. An invalid file emits a warning without discarding valid presets from the other layer.

{
  "orchestrate": {
    "provider": "openai-codex",
    "model": "gpt-5.6-sol",
    "thinkingLevel": "high",
    "instructions": "Delegate only independent, bounded work. Integrate and verify every result."
  }
}

instructions is optional. After /preset <name>, it is appended to the system prompt for later agent turns until another preset is selected. The active preset is stored on the session branch, so it survives reload, resume, and forks that include the selection. Use instructions for brief phase boundaries, not a duplicate project-wide policy.

Provider and model names must match pi --list-models.

Development

npm install
npm run verify
npm pack --dry-run