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

tau-laconic

v1.3.0

Published

Fewer words, sharper thought. Trust context; say only what silence can't.

Readme


laconic is a 300 word skill for AI coding agents inspired by caveman.

It cuts filler. It keeps meaning. It trusts context.

Every word earns its place.

Benchmarks

Caveman Benchmark

Claude Sonnet 4 via Langdock API. Each prompt: generic system prompt vs full laconic SKILL.md. Median of 3 runs per mode.

| Task | Normal (tokens) | Laconic (tokens) | Saved | vs Caveman | |------|---------------:|----------------:|------:|-----------:| | Explain React re-render bug | 885 | 68 | 92% | +5pp | | Fix auth middleware token expiry | 1059 | 39 | 96% | +13pp | | Set up PostgreSQL connection pool | 2167 | 189 | 91% | +7pp | | Explain git rebase vs merge | 996 | 95 | 90% | +32pp | | Refactor callback to async/await | 494 | 62 | 87% | +65pp | | Architecture: microservices vs monolith | 826 | 209 | 75% | +45pp | | Review PR for security issues | 940 | 126 | 87% | +46pp | | Docker multi-stage build | 2635 | 149 | 94% | +22pp | | Debug PostgreSQL race condition | 1370 | 49 | 96% | +15pp | | Implement React error boundary | 4096 | 400 | 90% | +3pp | | Average | 1547 | 139 | 90% | +25pp |

Range: 75%–96% savings across prompts. Caveman benchmarks averaged 64%.

[!IMPORTANT] Laconic cuts output tokens only.

cd benchmarks
pip install -r requirements.txt

echo "LANGDOCK_API_KEY=sk-your-key" > ../.env.local

python run.py --dry-run
python run.py
python run.py --update-readme

Examples

Prompt: "My Express auth middleware is letting expired JWT tokens through. The expiry check uses Date.now() compared to the token's exp field. What's wrong and how do I fix it?"

🗣️ Normal (~1,300 tokens)

Explains JWT spec, Unix timestamps vs JavaScript milliseconds, walks through middleware architecture, adds error handling, suggests libraries, and outputs a full refactored file (...)

Λ Laconic (19 tokens)

exp is in seconds. Date.now() is milliseconds.

if (Date.now() / 1000 > payload.exp) // expired

Caveman vs Laconic

| | Caveman | Laconic | |--|---------|---------| | Tone | Primitive | Terse | | Explanation | Normal | Trusts context, skips what reader knows | | Code | Normal | Just enough code | | Token savings | ~65% | ~90% |

Install

Any agent (40+ supported)

npx skills add GabrielBarberini/laconic

npx skills supports Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, and 40+ more. To install for a specific agent:

npx skills add GabrielBarberini/laconic -a cursor
npx skills add GabrielBarberini/laconic -a copilot
npx skills add GabrielBarberini/laconic -a cline
npx skills add GabrielBarberini/laconic -a windsurf

Pi

pi install https://github.com/GabrielBarberini/laconic

Or from npm:

pi install npm:tau-laconic

On pi you also get an extension: /laconic [on|off] (full laconic or off), natural-language triggers ("be laconic", "normal mode"), a laconic statusline, and per-project state in .pi/laconic-mode.json. It reads its rules from the same SKILL.md, so it never drifts.

Claude Code (plugin)

claude plugin marketplace add GabrielBarberini/laconic
claude plugin install laconic@laconic

Codex

  1. Clone repo
  2. Open Codex in repo
  3. Run /plugins
  4. Search Laconic
  5. Install plugin

Or copy the plugins/laconic/ directory into your Codex plugins folder.

Usage

Trigger with:

  • /laconic
  • "laconic mode"
  • "be laconic"

License

MIT — Sparta needed no walls. Neither does this license.