{
  "markdown": "# Browserless Plugin for Claude Code\n\nA Claude Code plugin that gives Claude direct access to the [Browserless.io](https://docs.browserless.io/rest-apis/intro) REST APIs: scrape webpages, take screenshots, generate PDFs, search the web, map site structures, and run custom browser automation, all from natural language.\n\n## Installation\n\nInstall from inside Claude Code:\n\n```\n/plugin marketplace add browserless/claude-plugin\n/plugin install browserless@browserless\n```\n\nTo pull future updates:\n\n```\n/plugin marketplace update browserless\n```\n\n### Manual install (local development)\n\nClone the repo and point Claude Code at the plugin directory:\n\n```bash\ngit clone https://github.com/browserless/claude-plugin.git\ncd claude-plugin\nclaude --plugin-dir .\n```\n\n## Setup\n\n### 1. Get a Browserless API token\n\nSign up for free at [browserless.io](https://www.browserless.io) and grab your API token.\n\n### 2. Authenticate\n\nRun the auth skill inside Claude Code:\n\n```\n/browserless:auth\n```\n\nThis will prompt you for your token and preferred API region (SFO, LON, or a custom URL), then save the credentials to `~/.browserless/.env`.\n\nAlternatively, set the environment variable directly:\n\n```bash\nexport BROWSERLESS_TOKEN=your-token-here\n```\n\n### 3. Start using skills\n\nOnce authenticated, all skills are available as slash commands:\n\n```\n/browserless:smart-scrape https://example.com\n/browserless:agent log into https://example.com and download my latest invoice\n/browserless:search what is browserless\n/browserless:map https://example.com\n/browserless:function click the login button on https://example.com\n/browserless:export save https://example.com with all assets for offline viewing\n/browserless:performance run a lighthouse audit on https://example.com\n/browserless:crawl crawl https://example.com up to 3 levels deep\n```\n\n## Skills\n\n| Skill | Command | Description | Example Prompt |\n|-------|---------|-------------|----------------|\n| **Auth** | `/browserless:auth` | Configure API token and region. Subcommands: `status`, `clear`, `region`. | |\n| **Agent** | `/browserless:agent` | Interactive, stateful browser session (via the MCP server) — navigate, click, type, log in, handle captchas/cookie banners, multi-step flows, file up/downloads. | `log into https://example.com and download my latest invoice` |\n| **Smart Scrape** | `/browserless:smart-scrape` | Scrape webpages with cascading strategies (HTTP fetch, proxy, headless browser, captcha solving). Returns markdown, HTML, screenshots, PDFs, or links. | `summarize the main content of https://news.ycombinator.com` |\n| **Search** | `/browserless:search` | Search the web and optionally scrape result pages. Supports web, news, and image sources with time-based filtering and content categories. | `find recent AI news en español from the last week` |\n| **Map** | `/browserless:map` | Discover and list all URLs on a website. Crawls sitemaps, pages, and subdomains with relevance-based search filtering. | `save a list of all URLs on https://browserless.io in json format` |\n| **Function** | `/browserless:function` | Execute custom Puppeteer JavaScript in a cloud browser. Run arbitrary automation scripts, interact with page elements, fill forms, and return structured data. | `load the ./scripts/sample-script.js file and run it using /function` |\n| **Export** | `/browserless:export` | Export a webpage in its native format, optionally bundling all resources (CSS, JS, images) into a ZIP archive for offline use. | `save https://example.com with all assets as a ZIP` |\n| **Performance** | `/browserless:performance` | Run a Lighthouse audit on a webpage. Get scores for performance, accessibility, best practices, SEO, and PWA. | `audit the performance and accessibility of https://example.com` |\n| **Crawl** | `/browserless:crawl` | Crawl an entire website starting from a seed URL, following links to configurable depth while scraping all discovered pages. | `crawl https://docs.browserless.io up to 3 levels deep` |\n\n> Screenshots, PDFs, and file downloads no longer have standalone skills — they're covered by `/browserless:smart-scrape` (screenshot/pdf via output formats) and `/browserless:agent` (downloads during a flow).\n\n\n## MCP Server (browser agent + tools)\n\nInstalling this plugin also registers the hosted **Browserless MCP server** (`https://mcp.browserless.io/mcp`), which adds tools the REST skills don't cover — most notably `browserless_agent`, an interactive browser-automation agent (navigate, click, type, snapshot, solve captchas, handle logins) that holds a live session across calls.\n\nIt reuses the same credentials: set `BROWSERLESS_TOKEN` (env var or via `/browserless:auth`). With no token, the hosted endpoint falls back to OAuth sign-in.\n\n| Tool | Description |\n|------|-------------|\n| `browserless_agent` | Interactive browser session — navigate, snapshot, click, type, multi-step automation |\n| `browserless_smartscraper` | Scrape a page (markdown/HTML/screenshot/PDF/links) |\n| `browserless_crawl` | Crawl a site to configurable depth |\n| `browserless_map` | Discover all URLs on a site |\n| `browserless_search` | Web/news/image search |\n| `browserless_function` | Run custom Puppeteer code |\n| `browserless_export` | Export a page with all assets |\n| `browserless_performance` | Lighthouse audit |\n\n## Auth Management\n\n| Command | Description |\n|---------|-------------|\n| `/browserless:auth` | Interactive setup — set token and region |\n| `/browserless:auth status` | Check if authentication is configured |\n| `/browserless:auth clear` | Remove saved credentials |\n| `/browserless:auth region` | Change API region without re-entering token |\n\nCredentials are stored in `~/.browserless/.env` with `600` permissions. The token resolution order is:\n\n1. `BROWSERLESS_TOKEN` environment variable (if set in shell)\n2. `~/.browserless/.env` file (written by `/browserless:auth`)\n\n## API Regions\n\n| Region | URL |\n|--------|-----|\n| SFO (US West, default) | `https://production-sfo.browserless.io` |\n| LON (Europe) | `https://production-lon.browserless.io` |\n| Custom | Any self-hosted or custom Browserless URL |\n\n## Plugin Structure\n\n```\n.claude-plugin/\n  plugin.json           # Plugin metadata\n.mcp.json               # Hosted Browserless MCP server (adds browserless_agent + tools)\nhooks/\n  hooks.json            # SessionStart hook config\nscripts/\n  check-auth.sh         # Warns if token is not configured\nskills/\n  auth/SKILL.md         # Authentication setup\n  agent/SKILL.md        # Interactive browser session (MCP-backed)\n  smart-scrape/SKILL.md # Web scraping (incl. screenshot/pdf via formats)\n  search/SKILL.md       # Web search\n  map/SKILL.md          # URL discovery\n  function/SKILL.md     # Custom Puppeteer code\n  export/SKILL.md       # Webpage export with resources\n  performance/SKILL.md  # Lighthouse audits\n  crawl/SKILL.md        # Multi-page website crawling\n```\n\n## API Reference\n\nMost skills map to a Browserless REST API endpoint; `agent` is served by the bundled MCP server over a WebSocket session instead. Full API documentation is available at [docs.browserless.io/rest-apis/intro](https://docs.browserless.io/rest-apis/intro).\n\n| Skill | Endpoint |\n|-------|----------|\n| Agent | MCP `browserless_agent` (WebSocket `/chromium/agent`) |\n| Smart Scrape | `POST /smart-scrape` |\n| Search | `POST /search` |\n| Map | `POST /map` |\n| Function | `POST /function` |\n| Export | `POST /export` |\n| Performance | `POST /performance` |\n| Crawl | `POST /crawl` |\n\n## License\n\nSSPL-1.0\n",
  "bytes": 7503,
  "sha": "85625ec0ad3da2b540215bb5a5c5aec8a1b722cb34d1014c874c386242aee463",
  "repo_slug": "browserless/claude-plugin",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_browserless_claude_plugin_browserless_7222109e/readme"
}