From browse
Scrape any webpage to markdown using the user's authenticated browser session. Use when you need to fetch web content, extract data from websites, scrape pages requiring login, convert HTML to markdown, or get content from social media profiles like Twitter/X or LinkedIn.
npx claudepluginhub pepijnsenders/browse-cliThis skill is limited to using the following tools:
Scrape any webpage to markdown using the user's authenticated browser session.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Share bugs, ideas, or general feedback.
Scrape any webpage to markdown using the user's authenticated browser session.
# macOS/Linux via Homebrew (recommended)
brew tap pepijnsenders/tap
brew install browse
# Or via npm
npm install -g @pep/browse-cli
After installing, load the Chrome extension:
chrome://extensions in Chrome/opt/homebrew/opt/browse/share/browse/extension~/.npm-global/lib/node_modules/@pep/browse-cli/extensionBefore using, ensure:
browse init# Scrape any URL to markdown
browse https://example.com
# Scrape with JSON metadata
browse https://example.com --json
browse <url> [options]
Options:
--json - Output JSON with url/title/content--html - Output pruned HTML instead of markdown--wait <ms> - Wait time after page load (default: 2000)--scroll <n> - Number of scrolls for infinite scroll pages (default: 0)browse init # Start background daemon
browse stop # Stop daemon
# Twitter/X profile
browse https://x.com/elonmusk
# LinkedIn profile
browse https://linkedin.com/in/satyanadella
# Any webpage
browse https://news.ycombinator.com
# Infinite scroll - load more content
browse https://x.com/elonmusk --scroll 5
# Slow pages - wait longer
browse https://example.com/slow --wait 10000
# JSON output
browse https://example.com --json
# Returns: {"url": "...", "title": "...", "content": "...markdown..."}
| Issue | Solution |
|---|---|
browse: command not found | Install via brew tap pepijnsenders/tap && brew install browse |
| "Daemon not running" | Run browse init |
| "Extension not connected" | Check Chrome is open, extension shows "ON" badge |
| Empty output | Try --wait 5000 --scroll 3 |