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

@hheei/codex-dollar-autcomplete

v0.1.1

Published

Dollar-triggered inline skill path references with cyan prompt highlighting for pi.

Readme

@hheei/codex-dollar-autcomplete

@hheei/codex-dollar-autcomplete adds $skill-name autocomplete, cyan prompt highlighting, prompt-time skill path expansion, and pi-loadout-aware skill ordering to pi.

It is intentionally different from /skill:name: it does not expand SKILL.md into the prompt. When you send a prompt, each recognized $skill-name token is replaced with the loaded skill's sourceInfo.path.

Behavior

Type $ in the prompt editor to list all loaded skills, or continue typing to filter by skill-name prefix only:

Review this using $lib

The picker renders three columns: skill name, source (User, Project, or Extension), and a multi-line description:

  librarian       User       Research open-source libraries with evidence-backed
                         answers and GitHub permalinks.
→ pi-subagents    Extension  Delegate work to subagents

Selecting the suggestion inserts the token:

Review this using $librarian

If $librarian matches a loaded skill, the token is highlighted cyan while you are editing the prompt. Unknown tokens such as $UNKNOWN are not highlighted.

When the prompt is sent, pi transforms it to:

Review this using /Users/me/.pi/agent/skills/librarian/SKILL.md

Multiple references in one prompt are supported:

Compare $librarian with $pi-subagents and keep $UNKNOWN untouched.

Only loaded pi skills are expanded. Unknown $NAME tokens are left unchanged.

pi-loadout support

When pi-loadout is installed and has an active skill selection, active skills are listed first. Inactive skills remain available at the bottom of the picker and render with the autocomplete description/muted theme style.

This lets $ stay useful even when pi-loadout trims the skills exposed to the model: active skills are prominent, while inactive skills can still be inserted manually as path references.

Example

Dollar skill picker showing active and inactive skills

Theme colors

The picker reuses pi's built-in editor autocomplete theme hooks: selectList.selectedText for the selected row, selectList.description for unselected descriptions, and selectList.scrollInfo for the scroll indicator.

Prompt $skill-name highlights use the main theme keys codexDollarHighlight, codexDollarSelected, mdCode, syntaxType, toolTitle, then the editor selectList.selectedText hook.

Install

From npm:

pi install npm:@hheei/codex-dollar-autcomplete

For local development from this repository:

pi install /path/to/codex-dollar-autcomplete

Or test for one run:

pi -e /path/to/codex-dollar-autcomplete

After installing into a running pi session, use /reload.

Recommended configuration

This package is meant to replace most interactive uses of /skill:name with $skill-name path references. To reduce duplicate skill command suggestions, consider disabling Pi's built-in skill slash commands:

{
  "enableSkillCommands": false
}

pi-loadout users can still control which skills are active in the model prompt; this package will read that active skill list and order the $ picker accordingly.

Development

npm run verify