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

opencode-firecrawl-web

v0.1.0

Published

Native Firecrawl tools for OpenCode 2: web search with filters, rendered page scraping, and developer index search. No skills or prompt additions.

Readme

opencode-firecrawl-web

Native Firecrawl tools for OpenCode 2: web search with filters, rendered page scraping, and search over technical docs, GitHub issues, and pull requests.

The plugin adds three tools and nothing else: no skills, no system prompt text, and no shell commands. Results come back in the tool output, so nothing is written to your project.

Install

opencode plugin add opencode-firecrawl-web

Or add it to plugins in ~/.config/opencode/opencode.json. To keep one search tool, turn off OpenCode's built-in web search:

{
  "$schema": "https://opencode.ai/config.json",
  "plugins": ["opencode-firecrawl-web"],
  "websearch": false
}

Keep OpenCode's webfetch for plain page and API fetches; it costs no credits.

Authentication

The plugin uses the first credential it finds:

  1. OpenCode's Firecrawl connection: run /connect, pick Firecrawl, and paste an API key or sign in.
  2. FIRECRAWL_API_KEY in the environment.
  3. The Firecrawl CLI's login (firecrawl login).

FIRECRAWL_API_URL, or the CLI's stored API URL, points the tools at a self-hosted Firecrawl. It must use HTTPS, or plain HTTP on localhost. dev_search also works without a credential, at a lower rate limit.

Tools

| Tool | What it does | | --- | --- | | web_search | Searches the web, news, or images. Filters: GitHub, research, or PDF categories, time range (tbs), included or excluded domains, location, and country. Returns 5 results per source by default, up to 20, and can extract a summary or markdown per result. | | web_scrape | Reads a JavaScript-heavy or blocked page as markdown, a summary, links, an answer to a question, or highlights. Supports render waits, mobile emulation, and proxy modes. | | dev_search | Searches the Firecrawl Developer Index of docs, GitHub issues, merged pull requests, and READMEs, and returns matched passages. Filters by artifact type, repository, docs domain, language, topic, license, and stars. |

Every call spends Firecrawl credits, except dev_search without a key. Results are marked as untrusted web content.

Permissions

The tools use OpenCode's own permission actions: web_search and dev_search check websearch, matched on the query, and web_scrape checks webfetch, matched on the URL. Agents allowed to search or fetch the web, such as the built-in explore agent, get these tools too, and a rule that denies websearch or webfetch removes them.

{
  "permissions": [{ "action": "webfetch", "resource": "*", "effect": "ask" }]
}

Development

mise install --locked
mise exec --locked -- bun install
mise exec --locked -- bun run validate      # typecheck and tests
mise exec --locked -- bun run pack:inspect  # files npm would publish

To try a local checkout, list its absolute path in plugins.

License

MIT