agent-browser - Automate browser interactions from the command line
Automates browser tasks such as navigation, form filling, clicking, screenshots, data extraction, web app testing, and authentication.
Tags
Updated: 2026-10-01Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Navigate to web pages
- Inspect interactive page elements
- Fill and submit forms
- Click and select elements
- Extract page text
- Capture screenshots and PDFs
- Persist browser session state
- Compare page states
- Connect to existing Chrome
- Automate iOS Safari
Inputs
- Website URLs
- Form and login data
- Element selectors
- Local file paths
- Session names
- Baseline snapshots
- Baseline screenshots
- iOS device identifiers
Outputs
- Browser navigation state
- Page snapshots
- Extracted page text
- Screenshots
- PDF files
- Saved authentication state
- Session state changes
- Snapshot and screenshot diffs
- Recorded session videos
- Profiler trace files
Requirements
- Bash access to agent-browser commands
- macOS with Xcode for iOS automation
- Appium with the XCUITest driver for iOS automation