Browser Automation Skill for Cursor

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

# Navigation
agent-browser open <url>              # Navigate
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs
agent-browser snapshot -i -C          # Include cursor-interactive elements
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser fill @e2 "text"         # Clear and type text
agent-browser type @e2 "text"         # Type without clearing
agent-browser select @e1 "option"     # Select dropdown option
agent-browser check @e1               # Check checkbox
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 url                 # Get current URL
agent-browser get title               # Get page title

# Wait
agent-browser wait @e1                # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page"    # Wait for URL pattern
agent-browser wait 2000               # Wait milliseconds

# Capture
agent-browser screenshot              # Screenshot to temp dir
agent-browser screenshot --full       # Full page screenshot
agent-browser pdf output.pdf          # Save as PDF

# Login once and save state
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Reuse in future sessions
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com
agent-browser session list

agent-browser --headed open https://example.com
agent-browser highlight @e1
agent-browser record start demo.webm

agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png

# List available iOS simulators
agent-browser device list

# Launch Safari on a specific device
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

# Same workflow — snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up
agent-browser -p ios screenshot mobile.png
agent-browser -p ios close

agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click

# Install CLI
curl -fsSL https://cli.inference.sh | sh && infsh login

# Open a page
infsh app run agentic-browser --function open --input '{"url": "https://example.com"}' --session new

# Start session
RESULT=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com/login"
}')
SESSION_ID=$(echo $RESULT | jq -r '.session_id')

# Fill and submit
infsh app run agentic-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e1", "text": "[email protected]"
}'
infsh app run agentic-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e2", "text": "password123"
}'
infsh app run agentic-browser --function interact --session $SESSION_ID --input '{
  "action": "click", "ref": "@e3"
}'

# Re-snapshot after navigation
infsh app run agentic-browser --function snapshot --session $SESSION_ID --input '{}'

# Close when done
infsh app run agentic-browser --function close --session $SESSION_ID --input '{}'

# Start with recording enabled
SESSION=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com",
  "record_video": true,
  "show_cursor": true
}' | jq -r '.session_id')

# ... perform actions ...

# Close to get the video file
infsh app run agentic-browser --function close --session $SESSION --input '{}'
# Returns: {"success": true, "video": <File>}

infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com",
  "proxy_url": "http://proxy.example.com:8080",
  "proxy_username": "user",
  "proxy_password": "pass"
}'

infsh app run agentic-browser --function interact --session $SESSION --input '{
  "action": "upload",
  "ref": "@e5",
  "file_paths": ["/path/to/file.pdf"]
}'

infsh app run agentic-browser --function execute --session $SESSION --input '{
  "code": "document.querySelectorAll(\"h2\").length"
}'
# Returns: {"result": "5", "screenshot": <File>}