Skills Guide

Browser Automation with agent-browser

VerifiedCaution

CLI for automating web interactions: navigate pages, fill forms, extract data, and test web apps. Perfect for repetitive tasks and programmatic website interaction.

Sby Skills Guide Bot
DevelopmentIntermediate
306/2/2026
Claude CodeCursorWindsurfCopilotCodex
#browser-automation#ai-agent#web-scraping#form-filling#screenshot

Recommended for

Backend developerClaude CodeCode reviewCursorFrontend developerCopilot

Our review

A CLI tool that enables AI agents to automate web interactions including navigation, form filling, clicking, screenshots, data extraction, and web app testing.

Strengths

  • Simple interface using element references (@e1, @e2) from snapshots
  • State persistence to reuse authenticated sessions across runs
  • Parallel sessions for interacting with multiple sites simultaneously
  • JSON output for automated data extraction and parsing

Limitations

  • Requires the agent to execute bash commands and interpret snapshot output
  • No built-in handling for complex JavaScript or highly dynamic SPAs
  • Depends on actual DOM rendering; vulnerable to selector changes
When to use it

Use this skill when you need to automate repetitive web tasks such as form submissions, data scraping, or verifying page states.

When not to use it

Do not use it for tasks requiring advanced visual analysis or interaction with applications that require client certificates or non-HTTP protocols.

Security analysis

Caution
Quality score92/100

The skill provides instructions for a browser automation CLI, which is a powerful tool for interacting with the web. While the skill itself does not instruct destructive or exfiltrating actions, it enables capabilities like navigating to any URL, filling forms, and saving authentication state. This could be misused for phishing, data theft, or unauthorized actions, thus caution is warranted.

Findings
  • •Tool allows arbitrary navigation and interaction with websites, which could be used for malicious purposes if misdirected.
  • •State persistence saves authentication cookies to a file, which could expose sensitive session data if mishandled.
  • •Capabilities of agent-browser may extend beyond documented commands, such as executing JavaScript, increasing potential risk.

Examples

Fill out a contact form
Navigate to https://example.com/contact and fill out the form with name 'John Doe', email 'john@example.com', and message 'Hello, I have a question.' Then submit the form.
Take a full-page screenshot
Take a full-page screenshot of the current page and save it to a file.
Extract product data
Open https://example.com/products and extract the names and prices of all products on the page.

name: agent-browser description: Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. allowed-tools: Bash(agent-browser:*)

Browser Automation with agent-browser

Core Workflow

Every browser automation follows this pattern:

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
  3. Interact: Use refs to click, fill, select
  4. Re-snapshot: After navigation or DOM changes, get fresh refs
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 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Essential Commands

# Navigation
agent-browser open <url>              # Navigate (aliases: goto, navigate)
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs (recommended)
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

Common Patterns

Form Submission

agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle

Authentication with State Persistence

# 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

Data Extraction

agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5           # Get specific element text
agent-browser get text body > page.txt  # Get all page text

# JSON output for parsing
agent-browser snapshot -i --json
agent-browser get text @e1 --json

Parallel Sessions

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

agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i

agent-browser session list

Visual Browser (Debugging)

agent-browser --headed open https://example.com
agent-browser highlight @e1          # Highlight element
agent-browser record start demo.webm # Record session

iOS Simulator (Mobile Safari)

# 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 as desktop - snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1          # Tap (alias for click)
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up         # Mobile-specific gesture

# Take screenshot
agent-browser -p ios screenshot mobile.png

# Close session (shuts down simulator)
agent-browser -p ios close

Requirements: macOS with Xcode, Appium (npm install -g appium && appium driver install xcuitest)

Real devices: Works with physical iOS devices if pre-configured. Use --device "<UDID>" where UDID is from xcrun xctrace list devices.

Ref Lifecycle (Important)

Refs (@e1, @e2, etc.) are invalidated when the page changes. Always re-snapshot after:

  • Clicking links or buttons that navigate
  • Form submissions
  • Dynamic content loading (dropdowns, modals)
agent-browser click @e5              # Navigates to new page
agent-browser snapshot -i            # MUST re-snapshot
agent-browser click @e1              # Use new refs

Semantic Locators (Alternative to Refs)

When refs are unavailable or unreliable, use semantic locators:

agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click

Deep-Dive Documentation

| Reference | When to Use | | -------------------------------------------------------------------- | --------------------------------------------------------- | | references/commands.md | Full command reference with all options | | references/snapshot-refs.md | Ref lifecycle, invalidation rules, troubleshooting | | references/session-management.md | Parallel sessions, state persistence, concurrent scraping | | references/authentication.md | Login flows, OAuth, 2FA handling, state reuse | | references/video-recording.md | Recording workflows for debugging and documentation | | references/proxy-support.md | Proxy configuration, geo-testing, rotating proxies |

Ready-to-Use Templates

| Template | Description | | ------------------------------------------------------------------------ | ----------------------------------- | | templates/form-automation.sh | Form filling with validation | | templates/authenticated-session.sh | Login once, reuse state | | templates/capture-workflow.sh | Content extraction with screenshots |

./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./output
Related skills

Next.js App Router Expert

Development

A skill that turns Claude into a Next.js App Router expert.

Claude CodeCursoradvanced
890
234
2,846
Admin

README Generator

Development

Creates professional and comprehensive README.md files for your projects.

claudeCursorWindsurfbeginner
259
72
821
Admin

API Documentation Writer

Development

Generates comprehensive API documentation in OpenAPI/Swagger format.

claudeCursorWindsurfintermediate
156
44
682
Admin