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

@blackbelt-technology/pi-dashboard-session-distiller

v0.7.0

Published

Offline miner: distill reusable artifacts from pi session JSONL logs

Downloads

645

Readme

@blackbelt-technology/pi-dashboard-session-distiller

Offline miner that distills reusable, verified knowledge from pi session JSONL logs. It is the deterministic engine behind the distill-session-knowledge pi skill; use the skill package @blackbelt-technology/pi-dashboard-distill-session-knowledge to load the discipline into a pi session, or use this engine directly as a CLI / library.

What it does

Walks the pi sessions for a project (newer than a persisted watermark), segments each trajectory, and extracts five signal classes anchored on objective outcomes:

  • fault — a tool error that a later same-tool retry resolves (isError flip).
  • user_correction — a human correction after an assistant action.
  • ask_user_decision — a recorded human decision.
  • procedure — an episode of >5 tool calls that ends verified-good.
  • documentation — a recurring how-to summary.

Only patterns that recur across >= N sessions (default 3) are promoted. Each promoted cluster is distilled into an artifact with provenance and a confidence score that decays with age and model change, then routed to a sink (skill_manage, memory, or docs).

Privacy

The miner is dry-run by default — nothing is written until you pass --apply. State (the watermark and below-threshold candidate store) is written to ~/.pi/agent/distill-session-knowledge/ on your machine; it is never bundled or transmitted. Distilled artifacts land only in your own local sinks after review. The emitted plan carries slugged signatures and provenance (session ids, model), not raw session payloads.

CLI

# dry-run over the current project (no writes)
npx distill-session-knowledge --cwd "$(git rev-parse --show-toplevel)"

# change the recurrence threshold and emit the routing plan as JSON
npx distill-session-knowledge --cwd "$(pwd)" --n 3 --json

# persist the watermark + candidate store and print the final plan
npx distill-session-knowledge --cwd "$(pwd)" --apply --json

Flags: --cwd <dir>, --n <k> (recurrence threshold), --sessions-dir <dir>, --apply, --json.

Library

import { run } from "@blackbelt-technology/pi-dashboard-session-distiller/main.js";

const result = run({ cwd: process.cwd(), n: 3 }); // dry-run
console.log(result.plan);

License

MIT