| name | browsing-with-robot |
| description | Automates browser interactions for web browsing, scraping, form filling, screenshots, and UI interaction. Use when the user needs to visit a webpage, check a live site, scrape content, fill forms, take screenshots, or interact with a web UI. |
| allowed-tools | Bash(robot:*) |
Browser Automation with robot
Setup
go install github.com/tmdgusya/robot.git@latest
git clone https://github.com/tmdgusya/robot.git /tmp/robot-build && cd /tmp/robot-build && go build -o /usr/local/bin/robot .
Quick start
robot start
robot navigate "https://example.com"
robot text
robot click "#my-button"
robot type "#email" "user@test.com"
robot screenshot
robot stop
Commands
Browser lifecycle
robot start
robot start --headless=false
robot stop
robot status
Navigation & extraction
robot navigate <url>
robot text
robot screenshot
Interaction
robot click <selector>
robot type <selector> <text>
Output
All responses are JSON. View screenshots with the Read tool.
{"ok": true, "url": "...", "title": "..."}
{"ok": true, "text": "..."}
{"ok": true, "path": "/tmp/robot/screenshot-1234.png"}
{"ok": false, "error": "...", "suggestion": "..."}
Example: Scrape page content
robot start
robot navigate "https://example.com"
robot text
robot stop
Example: Fill and submit form
robot start
robot navigate "https://example.com/form"
robot type "#email" "user@test.com"
robot type "#password" "secret"
robot click "button[type='submit']"
robot text
robot stop
Tips
- Start first. "daemon already running" error? Run
robot stop then robot start.
- Prefer
text over screenshot — text is token-cheap. Screenshot only for visual layout.
robot stop runs automatically when the session ends, but you can also run it manually between tasks.