linuxlewis/agent-browser
skills/agent-browser/SKILL.md
Browser automation using the agent-browser CLI. Use when user asks to browse websites, open webpages, interact with page elements, take screenshots, fill forms, click buttons, scrape content, or automate browser tasks.
$ install --global
skillsauthnpx skillsauth add linuxlewis/agent-skills agent-browserInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 5, 2026, 6:45 AM126.9s2 files scanned
SKILL.md
- name:
- agent-browser
- description:
- Browser automation using the agent-browser CLI. Use when user asks to browse websites, open webpages, interact with page elements, take screenshots, fill forms, click buttons, scrape content, or automate browser tasks.
- license:
- MIT
- compatibility:
- Requires agent-browser CLI (npm install -g agent-browser)
- author:
- linuxlewis
- version:
- 1.0.0
Agent Browser
Browser automation using the agent-browser CLI - a fast, headless browser automation tool for AI agents.
Installation
npm install -g agent-browser
agent-browser install # Install browser binaries
Quick Start
# Navigate to a URL
agent-browser open https://example.com
# Get accessibility snapshot (shows refs like @e1, @e2)
agent-browser snapshot -i
# Click using ref from snapshot
agent-browser click @e2
# Type into an element
agent-browser fill @e3 "hello world"
# Take screenshot
agent-browser screenshot output.png
Workflow Pattern
- Open - Navigate to the target URL
- Snapshot - Get the accessibility tree to see available elements
- Interact - Use refs (@e1, @e2, etc.) to interact with elements
- Verify - Take a snapshot or screenshot to verify state
Core Commands
See references/commands.md for the complete command reference.
Navigation
agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
Interaction
agent-browser click <sel> # Click element (or @ref)
agent-browser fill <sel> <text> # Clear and fill
agent-browser press <key> # Press key (Enter, Tab, etc.)
agent-browser select <sel> <val> # Select dropdown option
Getting Information
agent-browser snapshot # Accessibility tree with refs
agent-browser snapshot -i # Interactive elements only
agent-browser get text <sel> # Get element text
agent-browser get url # Get current URL
Capture
agent-browser screenshot [path] # Take screenshot
agent-browser screenshot --full # Full page screenshot
agent-browser pdf <path> # Save as PDF
Sessions
Use sessions to maintain browser state across commands:
agent-browser --session myproject open https://example.com
agent-browser --session myproject snapshot
agent-browser --session myproject click @e1
Selectors
- Refs:
@e1,@e2(from snapshot output) - preferred - CSS:
#id,.class,div > span - Text:
text=Submit - Role:
role=button[name="Submit"]
Best Practices
- Always snapshot first - Get the accessibility tree before interacting
- Use refs - Prefer
@e1refs from snapshot over CSS selectors - Use sessions - Maintain state across multiple commands
- Wait appropriately - Use
waitfor dynamic content - Verify actions - Snapshot or screenshot after interactions
Related Skills
linuxlewis/ralph-runner
development
VerifiedTrustedCommunity
Run Ralph Wiggum autonomous coding loops. Use when user asks to run ralph, start autonomous coding, execute a PRD, implement features from a task list, or wants Claude Code to work through user stories iteratively.
1SKILL.mdUpdated Jun 5, 2026
linuxlewis/pr-responder
development
VerifiedTrustedCommunity
Review and respond to GitHub PR comments. Use when analyzing PR feedback, determining which comments to address, classifying review comments by priority, or implementing fixes for code review feedback.
1SKILL.mdUpdated Jun 5, 2026
linuxlewis/openclaw-notify
data-ai
VerifiedTrustedCommunity
Notify OpenClaw gateway when background tasks complete. Use when you were dispatched by OpenClaw/TARS for background work and need to ping the user that you're done, failed, or blocked.
1SKILL.mdUpdated Jun 5, 2026
linuxlewis/linuxlewis-code-review
development
VerifiedTrustedCommunity
Apply linuxlewis's code review style to pull requests, local diffs, or proposed code changes. Use when asked to review code the way linuxlewis would, emulate Sam Bolgert's review strategy, predict likely PR feedback, or explain linuxlewis's review profile.
1SKILL.mdUpdated Jun 5, 2026