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-commandcode-pricing

v0.1.0

Published

Command Code plan pricing in pi — /go-pricing, /goat-pricing, /pro-pricing, /max-pricing popups scraped live from commandcode.ai

Readme

pi-commandcode-pricing

Command Code plan pricing inside pi — scrollable popup with sort, search, and request limits, scraped live from the official docs pages (no public pricing API exists).

Install

pi install npm:pi-commandcode-pricing
# or from GitHub:
pi install git:github.com/LemonPhase/pi-commandcode-pricing

Or try without installing:

pi -e git:github.com/LemonPhase/pi-commandcode-pricing

Commands

| Command | Shows | |---------|-------| | /go-pricing | Go plan — 40 Go-eligible models with per-token prices (windows aren't published per-model on the Go page) | | /goat-pricing | GOAT plan — per-model pricing, intel, request limits (free models included) | | /pro-pricing | Pro plan — 46 models across three credit tables | | /max-pricing | Max 10× / Max 20× — both credit tiers side by side (they differ only in credit amounts) |

Keys inside a popup: Tab cycles sort (Credits → Intelligence → Plan intel/mo), / filters by model name (Backspace on empty cancels), ↑↓/jk scroll, ←→/hl pan columns when overflowing, PgUp/PgDn/u d page, g/G top/end, Esc clears search then closes.

Where the data comes from

  • Each command reads its own plan page (commandcode.ai/docs/plans/<plan>) for prices, credits, and request windows.
  • Intelligence scores always come from the GOAT page's embedded flight JSON, which covers the whole model catalogue — the same scores on every plan.
  • Value sort ranks by intel per blended $/MTok (0.75·input + 0.25·output, matching the site's own calculator); free models pin to the top. That's the plan-blind API-price lens.
  • Intel/mo is the plan-holder's lens: intel × the plan's monthly credit allowance for that model ÷ blended cost — the scored intelligence×MTok your plan buys per month. Credits differ per model, so this sees what Intel/$ can't. Max's two tiers show joined (448/897); Go shows — (no per-model allowances published); free models show ∞. Plan sort ranks by it.
  • No caching — every command fetches fresh. Pages are ~300–650KB; expect a short delay.

Development

npm install
./test/fetch-fixtures.sh   # refresh saved plan-page fixtures
node test/run.mjs          # headless checks against fixtures

To load a local checkout into pi without installing:

pi install /path/to/pi-commandcode-pricing   # local-path package, loads live from disk

License

MIT