Help us improve
Share bugs, ideas, or general feedback.
From stagehand
Automates web browser interactions via CLI using natural language. Supports navigation, data extraction, screenshots, form filling, and click actions. Remote mode with Browserbase provides CAPTCHA solving, residential proxies, and anti-detection features.
npx claudepluginhub browserbase/skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/stagehand:browserThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Automate browser interactions using the browse CLI with Claude.
Reference for agent-browser commands to navigate pages, snapshot elements, interact (click/fill/type), extract data. For web testing, form automation, screenshots.
Controls a headless browser via Vercel's agent-browser CLI for navigation, form filling, screenshots, and scraping using accessibility refs.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Automate browser interactions using the browse CLI with Claude.
Before running any browser commands, verify the CLI is available:
which browse || npm install -g browse
The CLI supports explicit per-command environment flags. If you do nothing, the next session defaults to Browserbase when BROWSERBASE_API_KEY is set and to local otherwise.
browse open <url> --local starts a clean isolated local browserbrowse open <url> --auto-connect attaches to an already-running debuggable Chrome; use --local when no debuggable Chrome is availablebrowse open <url> --cdp <port|url> attaches to a specific CDP targetbrowse open <url> --remote starts a Browserbase sessionBROWSERBASE_API_KEY is setbrowse open <url> --localbrowse open <url> --auto-connectMost driver commands work across local, remote, and CDP sessions after the daemon starts.
browse open <url> # Go to URL
browse open <url> --local # Go to URL in a clean local browser
browse open <url> --remote # Go to URL in a Browserbase session
browse reload # Reload current page
browse back # Go back in history
browse forward # Go forward in history
browse snapshot # Get accessibility tree with element refs (fast, structured)
browse screenshot --path <path> # Take visual screenshot (slow, uses vision tokens)
browse get url # Get current URL
browse get title # Get page title
browse get text <selector> # Get text content (use "body" for all text)
browse get html <selector> # Get HTML content of element
browse get value <selector> # Get form field value
Use browse snapshot as your default for understanding page state — it returns the accessibility tree with element refs you can use to interact. Only use browse screenshot when you need visual context (layout, images, debugging).
browse click <ref> # Click element by ref from snapshot (e.g., @0-5)
browse type <text> # Type text into focused element
browse fill <selector> <value> # Fill input; add --press-enter if Enter is needed
browse select <selector> <values...> # Select dropdown option(s)
browse press <key> # Press key (Enter, Tab, Escape, Cmd+A, etc.)
browse mouse drag <fromX> <fromY> <toX> <toY> # Drag from one point to another
browse mouse scroll <x> <y> <deltaX> <deltaY> # Scroll at coordinates
browse highlight <selector> # Highlight element on page
browse is visible <selector> # Check if element is visible
browse is checked <selector> # Check if element is checked
browse wait <type> [arg] # Wait for: load, selector, timeout
browse stop # Stop the browser daemon
browse status # Check daemon status and resolved mode
browse tab list # List all open tabs
browse tab switch <index-or-target-id> # Switch to tab by index or target ID
browse tab close [index-or-target-id] # Close tab
If the environment matters, put --local, --remote, --auto-connect, or --cdp <port|url> on the first browser command.
browse open <url> --local or browse open <url> --remote — navigate to the pagebrowse snapshot — read the accessibility tree to understand page structure and get element refsbrowse click <ref> / browse type <text> / browse fill <selector> <value> — interact using refs from snapshotbrowse snapshot — confirm the action workedbrowse stop — close the browser when donebrowse open https://example.com
browse snapshot # see page structure + element refs
browse click @0-5 # click element with ref 0-5
browse get title
browse stop
| Feature | Local | Browserbase |
|---|---|---|
| Speed | Faster | Slightly slower |
| Setup | Chrome required | API key required |
| Reuse existing local cookies | With browse open <url> --auto-connect | N/A |
| Verified browser | No | Yes (Browserbase Verified browser via Identity) |
| CAPTCHA solving | No | Yes (automatic reCAPTCHA/hCaptcha) |
| Residential proxies | No | Yes (201 countries, geo-targeting) |
| Session persistence | No | Yes (cookies/auth persist via contexts) |
| Best for | Development/simple pages | Protected sites, Browserbase Identity + Verified access, production scraping |
browse open <url> --local for clean state, browse open <url> --auto-connect for existing local credentials, and browse open <url> --remote for protected sitesbrowse open first before interactingbrowse snapshot to check page state — it's fast and gives you element refsbrowse click @0-5browse stop when done to clean up the browser session and clear the env overridebrowse stop, then check browse status. If it still says running, kill the zombie daemon with pkill -f "browse.*daemon", then retry browse openbrowse open <url> --auto-connect if you already have a debuggable Chrome running, or switch to browse open <url> --remotebrowse snapshot to see available elements and their refsSwitch to remote when you detect: CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot detection pages ("Checking your browser..."), HTTP 403/429, empty pages on sites that should have content, or the user asks for it.
Don't switch for simple sites (docs, wikis, public APIs, localhost).
browse open <url> --local # clean isolated local browser
browse open <url> --auto-connect # attach to existing debuggable Chrome
browse open <url> --remote # Browserbase session
Mode flags are applied when a session starts. After browse stop, the next start falls back to env-var-based auto detection. Use browse status to inspect the resolved mode and target while the daemon is running.
For detailed examples, see EXAMPLES.md. For API reference, see REFERENCE.md.