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

keyless-agent-recipes

v0.1.0

Published

12 ready-to-run AI agent prompt recipes (TL;DR summarizer, code review, meeting notes → actions, RFP response, changelog generator, more). Works with any free OpenAI-compatible LLM endpoint — no API key required. MIT licensed.

Readme

keyless-agent-recipes

12 ready-to-run AI agent prompts. Works with any free OpenAI-compatible LLM endpoint — no API key required. MIT licensed.

The prompts are field-tested system + user templates for the most common agent jobs: summarization, code review, meeting notes → actions, RFP outlines, changelog from git commits, support triage, and more. Designed to be dropped into any LLM client (keylessai, openai SDK with custom baseURL, raw fetch).

Install

npm install keyless-agent-recipes

Use

import { getRecipe, fillTemplate } from 'keyless-agent-recipes';

const r = getRecipe('01-tldr-summarizer');
const { messages } = fillTemplate('01-tldr-summarizer', {
  TEXT: 'Long article body goes here…',
});

// Pass `messages` to whatever LLM client you have:
const response = await fetch('https://text.pollinations.ai/openai', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ model: 'openai', messages }),
});

Works with the free, no-key keylessai router too:

import { streamChat } from 'keylessai';
import { fillTemplate } from 'keyless-agent-recipes';

const { messages } = fillTemplate('04-code-review', {
  DIFF: '...',
  LANG: 'typescript',
});
for await (const chunk of streamChat({ provider: 'auto', messages })) {
  if (chunk?.type === 'content') process.stdout.write(chunk.text);
}

The 12 recipes

| ID | What it does | |---|---| | 01-tldr-summarizer | Long text → 5-bullet executive summary | | 02-cold-email-replier | Inbound cold pitch → polite, brief response | | 03-meeting-notes-to-actions | Raw notes → decisions + action items + owners | | 04-code-review | Diff → ranked security + readability comments | | 05-resume-bullet-rewriter | Vague responsibility → quantified STAR bullet | | 06-tweet-thread-from-blog | Long-form post → 6-10 tweet thread | | 07-bug-report-to-test-case | Vague report → reproducible steps | | 08-spec-from-feature-request | Feature request → 1-page mini PRD | | 09-csv-cleaner | Messy CSV sample → schema + transformation rules | | 10-customer-support-triage | Ticket → category + priority + draft response | | 11-rfp-response-skeleton | RFP requirements → response outline | | 12-changelog-from-commits | Git log → user-facing release notes |

Get the full definitions with import { recipes } from 'keyless-agent-recipes'.

API

recipes — Array

The full recipe set. Each entry has id, name, use, system, user_template.

getRecipe(id) — Function

Returns one recipe or null.

list() — Function

Returns all recipe IDs.

fillTemplate(id, vars) — Function

Substitutes {{VAR}} placeholders in user_template and returns:

{ system: string, user: string, messages: [...] }

messages is ready to pass to any OpenAI-compatible client.

Browser demo

Try every recipe live in your browser (no install): civic-letters.pages.dev/pack/agent-recipes/example.html

License

MIT. Fork, ship, sell, modify. Attribution welcome but not required.

Author

drlordbasil · github · keylessai

If this package saved you time, buy me a coffee ☕.