| name | agent-browser |
| description | Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages. |
| allowed-tools | Bash(agent-browser:*) |
Browser Automation with agent-browser
Core Workflow
agent-browser open <url> — navigate
agent-browser snapshot -i — get interactive elements with refs (@e1, @e2)
- Interact using refs from snapshot
- Re-snapshot after navigation or DOM changes
Common Commands
agent-browser open <url>
agent-browser back | forward | reload | close
agent-browser snapshot -i
agent-browser snapshot -c
agent-browser snapshot -s "#selector"
agent-browser click @e1
agent-browser fill @e2 "text"
agent-browser type @e2 "text"
agent-browser press Enter
agent-browser select @e1 "value"
agent-browser scroll down 500
agent-browser hover @e1
agent-browser check @e1 | uncheck @e1
agent-browser get text @e1
agent-browser get value @e1
agent-browser get url | get title
agent-browser screenshot
agent-browser screenshot path.png
agent-browser screenshot --full
agent-browser wait @e1
agent-browser wait 2000
agent-browser wait --text "Success"
agent-browser wait --load networkidle
agent-browser is visible @e1
agent-browser is enabled @e1
agent-browser eval "document.title"
Semantic Locators (alternative to refs)
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
Debugging
agent-browser open <url> --headed
agent-browser console
agent-browser errors
agent-browser highlight @e1
For full command reference: agent-browser --help