mcpField
A
agent-browser

agent-browser

github.com/actionbookAgent workflows1.6k136 installsUpdated 2w ago
Repository

About agent-browser

agent-browser is a command-line browser automation skill for agents. It provides a snapshot-and-reference workflow for navigating pages, interacting with elements, and retrieving page information.

Key features

  1. 01Navigate to web pages
  2. 02Inspect accessibility snapshots
  3. 03Interact using element references
  4. 04Read text, title, and URL
  5. 05Wait for elements or page loads

Use cases

  1. 01Fill and submit web forms
  2. 02Inspect interactive page elements
  3. 03Extract text from a page

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/actionbook/actionbook --skill agent-browser

After installing, type/agent-browserin Claude Code to confirm it loaded.

Details

From the project README

Browser Automation with agent-browser

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
  3. Interact using refs from the snapshot
  4. Re-snapshot after navigation or significant DOM changes
  5. Always close: agent-browser close

Commands

Navigation
agent-browser open <url>      # Navigate to URL
agent-browser close           # Close browser (ALWAYS do this)
Snapshot (page analysis)
agent-browser snapshot        # Full accessibility tree
agent-browser snapshot -i     # Interactive elements only (recommended)
Interactions (use @refs from snapshot)
agent-browser click @e1           # Click
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser scroll down 500     # Scroll page
Get information
agent-browser get text @e1        # Get element text
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
Wait
agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --load networkidle      # Wait for network idle

Example: Form submission (request-website)

# Open Actionbook request page
agent-browser open "https://actionbook.app/request-website"

# Get form elements
agent-browser snapshot -i
# Output shows: textbox "Site URL" [ref=e1], textbox "Email" [ref=e2], textbox "Use Case" [ref=e3], button "Submit" [ref=e4]

# Fill form
agent-browser fill @e1 "https://example.com/products"
agent-browser fill @e2 "[email protected]"
agent-browser fill @e3 "Scraping product catalog"

# Submit
agent-browser click @e4
agent-browser wait --load networkidle

# Verify submission
agent-browser snapshot -i

# Close browser
agent-browser close

Permission Required

Add to .claude/settings.local.json:

{
  "permissions": {
    "allow": [
      "Bash(agent-browser *)"
    ]
  }
}

Or run ./setup.sh to configure automatically.

Comments

Markdown supported