agent-browser 0.6.0 → 0.7.2

package/skills/agent-browser/SKILL.md

@@ -26,15 +26,20 @@ agent-browser close             # Close browser
 ## Commands
 
 ### Navigation
+
 ```bash
-agent-browser open <url>      # Navigate to URL
+agent-browser open <url>      # Navigate to URL (aliases: goto, navigate)
+                              # Supports: https://, http://, file://, about:, data://
+                              # Auto-prepends https:// if no protocol given
 agent-browser back            # Go back
 agent-browser forward         # Go forward
 agent-browser reload          # Reload page
-agent-browser close           # Close browser
+agent-browser close           # Close browser (aliases: quit, exit)
+agent-browser connect 9222    # Connect to browser via CDP port
 ```
 
 ### Snapshot (page analysis)
+
 ```bash
 agent-browser snapshot            # Full accessibility tree
 agent-browser snapshot -i         # Interactive elements only (recommended)
@@ -44,27 +49,30 @@ agent-browser snapshot -s "#main" # Scope to CSS selector
 ```
 
 ### Interactions (use @refs from snapshot)
+
 ```bash
 agent-browser click @e1           # Click
 agent-browser dblclick @e1        # Double-click
 agent-browser focus @e1           # Focus element
 agent-browser fill @e2 "text"     # Clear and type
 agent-browser type @e2 "text"     # Type without clearing
-agent-browser press Enter         # Press key
+agent-browser press Enter         # Press key (alias: key)
 agent-browser press Control+a     # Key combination
 agent-browser keydown Shift       # Hold key down
 agent-browser keyup Shift         # Release key
 agent-browser hover @e1           # Hover
 agent-browser check @e1           # Check checkbox
 agent-browser uncheck @e1         # Uncheck checkbox
-agent-browser select @e1 "value"  # Select dropdown
-agent-browser scroll down 500     # Scroll page
-agent-browser scrollintoview @e1  # Scroll element into view
+agent-browser select @e1 "value"  # Select dropdown option
+agent-browser select @e1 "a" "b"  # Select multiple options
+agent-browser scroll down 500     # Scroll page (default: down 300px)
+agent-browser scrollintoview @e1  # Scroll element into view (alias: scrollinto)
 agent-browser drag @e1 @e2        # Drag and drop
 agent-browser upload @e1 file.pdf # Upload files
 ```
 
 ### Get information
+
 ```bash
 agent-browser get text @e1        # Get element text
 agent-browser get html @e1        # Get innerHTML
@@ -74,9 +82,11 @@ agent-browser get title           # Get page title
 agent-browser get url             # Get current URL
 agent-browser get count ".item"   # Count matching elements
 agent-browser get box @e1         # Get bounding box
+agent-browser get styles @e1      # Get computed styles (font, color, bg, etc.)
 ```
 
 ### Check state
+
 ```bash
 agent-browser is visible @e1      # Check if visible
 agent-browser is enabled @e1      # Check if enabled
@@ -84,6 +94,7 @@ agent-browser is checked @e1      # Check if checked
 ```
 
 ### Screenshots & PDF
+
 ```bash
 agent-browser screenshot          # Screenshot to stdout
 agent-browser screenshot path.png # Save to file
@@ -92,25 +103,30 @@ agent-browser pdf output.pdf      # Save as PDF
 ```
 
 ### Video recording
+
 ```bash
 agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
 agent-browser click @e1                   # Perform actions
 agent-browser record stop                 # Stop and save video
 agent-browser record restart ./take2.webm # Stop current + start new recording
 ```
-Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it automatically returns to your current page. For smooth demos, explore first, then start recording.
+
+Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it
+automatically returns to your current page. For smooth demos, explore first, then start recording.
 
 ### Wait
+
 ```bash
 agent-browser wait @e1                     # Wait for element
 agent-browser wait 2000                    # Wait milliseconds
-agent-browser wait --text "Success"        # Wait for text
-agent-browser wait --url "**/dashboard"    # Wait for URL pattern
-agent-browser wait --load networkidle      # Wait for network idle
-agent-browser wait --fn "window.ready"     # Wait for JS condition
+agent-browser wait --text "Success"        # Wait for text (or -t)
+agent-browser wait --url "**/dashboard"    # Wait for URL pattern (or -u)
+agent-browser wait --load networkidle      # Wait for network idle (or -l)
+agent-browser wait --fn "window.ready"     # Wait for JS condition (or -f)
 ```
 
 ### Mouse control
+
 ```bash
 agent-browser mouse move 100 200      # Move mouse
 agent-browser mouse down left         # Press button
@@ -119,26 +135,36 @@ agent-browser mouse wheel 100         # Scroll wheel
 ```
 
 ### Semantic locators (alternative to refs)
+
 ```bash
 agent-browser find role button click --name "Submit"
 agent-browser find text "Sign In" click
+agent-browser find text "Sign In" click --exact      # Exact match only
 agent-browser find label "Email" fill "user@test.com"
+agent-browser find placeholder "Search" type "query"
+agent-browser find alt "Logo" click
+agent-browser find title "Close" click
+agent-browser find testid "submit-btn" click
 agent-browser find first ".item" click
-agent-browser find nth 2 "a" text
+agent-browser find last ".item" click
+agent-browser find nth 2 "a" hover
 ```
 
 ### Browser settings
+
 ```bash
-agent-browser set viewport 1920 1080      # Set viewport size
-agent-browser set device "iPhone 14"      # Emulate device
-agent-browser set geo 37.7749 -122.4194   # Set geolocation
-agent-browser set offline on              # Toggle offline mode
-agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
-agent-browser set credentials user pass   # HTTP basic auth
-agent-browser set media dark              # Emulate color scheme
+agent-browser set viewport 1920 1080          # Set viewport size
+agent-browser set device "iPhone 14"          # Emulate device
+agent-browser set geo 37.7749 -122.4194       # Set geolocation (alias: geolocation)
+agent-browser set offline on                  # Toggle offline mode
+agent-browser set headers '{"X-Key":"v"}'     # Extra HTTP headers
+agent-browser set credentials user pass       # HTTP basic auth (alias: auth)
+agent-browser set media dark                  # Emulate color scheme
+agent-browser set media light reduced-motion  # Light mode + reduced motion
 ```
 
 ### Cookies & Storage
+
 ```bash
 agent-browser cookies                     # Get all cookies
 agent-browser cookies set name value      # Set cookie
@@ -150,6 +176,7 @@ agent-browser storage local clear         # Clear all
 ```
 
 ### Network
+
 ```bash
 agent-browser network route <url>              # Intercept requests
 agent-browser network route <url> --abort      # Block requests
@@ -160,31 +187,73 @@ agent-browser network requests --filter api    # Filter requests
 ```
 
 ### Tabs & Windows
+
 ```bash
 agent-browser tab                 # List tabs
 agent-browser tab new [url]       # New tab
-agent-browser tab 2               # Switch to tab
-agent-browser tab close           # Close tab
+agent-browser tab 2               # Switch to tab by index
+agent-browser tab close           # Close current tab
+agent-browser tab close 2         # Close tab by index
 agent-browser window new          # New window
 ```
 
 ### Frames
+
 ```bash
 agent-browser frame "#iframe"     # Switch to iframe
 agent-browser frame main          # Back to main frame
 ```
 
 ### Dialogs
+
 ```bash
 agent-browser dialog accept [text]  # Accept dialog
 agent-browser dialog dismiss        # Dismiss dialog
 ```
 
 ### JavaScript
+
 ```bash
 agent-browser eval "document.title"   # Run JavaScript
 ```
 
+## Global options
+
+```bash
+agent-browser --session <name> ...    # Isolated browser session
+agent-browser --json ...              # JSON output for parsing
+agent-browser --headed ...            # Show browser window (not headless)
+agent-browser --full ...              # Full page screenshot (-f)
+agent-browser --cdp <port> ...        # Connect via Chrome DevTools Protocol
+agent-browser -p <provider> ...       # Cloud browser provider (--provider)
+agent-browser --proxy <url> ...       # Use proxy server
+agent-browser --headers <json> ...    # HTTP headers scoped to URL's origin
+agent-browser --executable-path <p>   # Custom browser executable
+agent-browser --extension <path> ...  # Load browser extension (repeatable)
+agent-browser --help                  # Show help (-h)
+agent-browser --version               # Show version (-V)
+agent-browser <command> --help        # Show detailed help for a command
+```
+
+### Proxy support
+
+```bash
+agent-browser --proxy http://proxy.com:8080 open example.com
+agent-browser --proxy http://user:pass@proxy.com:8080 open example.com
+agent-browser --proxy socks5://proxy.com:1080 open example.com
+```
+
+## Environment variables
+
+```bash
+AGENT_BROWSER_SESSION="mysession"            # Default session name
+AGENT_BROWSER_EXECUTABLE_PATH="/path/chrome" # Custom browser path
+AGENT_BROWSER_EXTENSIONS="/ext1,/ext2"       # Comma-separated extension paths
+AGENT_BROWSER_PROVIDER="browserbase"         # Cloud browser provider
+AGENT_BROWSER_STREAM_PORT="9223"             # WebSocket streaming port
+AGENT_BROWSER_HOME="/path/to/agent-browser"  # Custom install location (for daemon.js)
+```
+
 ## Example: Form submission
 
 ```bash
@@ -227,6 +296,7 @@ agent-browser session list
 ## JSON output (for parsing)
 
 Add `--json` for machine-readable output:
+
 ```bash
 agent-browser snapshot -i --json
 agent-browser get text @e1 --json
@@ -235,18 +305,45 @@ agent-browser get text @e1 --json
 ## Debugging
 
 ```bash
-agent-browser open example.com --headed              # Show browser window
-agent-browser console                                # View console messages
-agent-browser errors                                 # View page errors
-agent-browser record start ./debug.webm   # Record from current page
-agent-browser record stop                            # Save recording
-agent-browser open example.com --headed  # Show browser window
-agent-browser --cdp 9222 snapshot        # Connect via CDP
-agent-browser console                    # View console messages
-agent-browser console --clear            # Clear console
-agent-browser errors                     # View page errors
-agent-browser errors --clear             # Clear errors
-agent-browser highlight @e1              # Highlight element
-agent-browser trace start                # Start recording trace
-agent-browser trace stop trace.zip       # Stop and save trace
+agent-browser --headed open example.com   # Show browser window
+agent-browser --cdp 9222 snapshot         # Connect via CDP port
+agent-browser connect 9222                # Alternative: connect command
+agent-browser console                     # View console messages
+agent-browser console --clear             # Clear console
+agent-browser errors                      # View page errors
+agent-browser errors --clear              # Clear errors
+agent-browser highlight @e1               # Highlight element
+agent-browser trace start                 # Start recording trace
+agent-browser trace stop trace.zip        # Stop and save trace
+agent-browser record start ./debug.webm   # Record video from current page
+agent-browser record stop                 # Save recording
+```
+
+## Deep-dive documentation
+
+For detailed patterns and best practices, see:
+
+| Reference | Description |
+|-----------|-------------|
+| [references/snapshot-refs.md](references/snapshot-refs.md) | Ref lifecycle, invalidation rules, troubleshooting |
+| [references/session-management.md](references/session-management.md) | Parallel sessions, state persistence, concurrent scraping |
+| [references/authentication.md](references/authentication.md) | Login flows, OAuth, 2FA handling, state reuse |
+| [references/video-recording.md](references/video-recording.md) | Recording workflows for debugging and documentation |
+| [references/proxy-support.md](references/proxy-support.md) | Proxy configuration, geo-testing, rotating proxies |
+
+## Ready-to-use templates
+
+Executable workflow scripts for common patterns:
+
+| Template | Description |
+|----------|-------------|
+| [templates/form-automation.sh](templates/form-automation.sh) | Form filling with validation |
+| [templates/authenticated-session.sh](templates/authenticated-session.sh) | Login once, reuse state |
+| [templates/capture-workflow.sh](templates/capture-workflow.sh) | Content extraction with screenshots |
+
+Usage:
+```bash
+./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
 ```

package/skills/agent-browser/references/authentication.md

@@ -0,0 +1,188 @@
+# Authentication Patterns
+
+Patterns for handling login flows, session persistence, and authenticated browsing.
+
+## Basic Login Flow
+
+```bash
+# Navigate to login page
+agent-browser open https://app.example.com/login
+agent-browser wait --load networkidle
+
+# Get form elements
+agent-browser snapshot -i
+# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Sign In"
+
+# Fill credentials
+agent-browser fill @e1 "user@example.com"
+agent-browser fill @e2 "password123"
+
+# Submit
+agent-browser click @e3
+agent-browser wait --load networkidle
+
+# Verify login succeeded
+agent-browser get url  # Should be dashboard, not login
+```
+
+## Saving Authentication State
+
+After logging in, save state for reuse:
+
+```bash
+# Login first (see above)
+agent-browser open https://app.example.com/login
+agent-browser snapshot -i
+agent-browser fill @e1 "user@example.com"
+agent-browser fill @e2 "password123"
+agent-browser click @e3
+agent-browser wait --url "**/dashboard"
+
+# Save authenticated state
+agent-browser state save ./auth-state.json
+```
+
+## Restoring Authentication
+
+Skip login by loading saved state:
+
+```bash
+# Load saved auth state
+agent-browser state load ./auth-state.json
+
+# Navigate directly to protected page
+agent-browser open https://app.example.com/dashboard
+
+# Verify authenticated
+agent-browser snapshot -i
+```
+
+## OAuth / SSO Flows
+
+For OAuth redirects:
+
+```bash
+# Start OAuth flow
+agent-browser open https://app.example.com/auth/google
+
+# Handle redirects automatically
+agent-browser wait --url "**/accounts.google.com**"
+agent-browser snapshot -i
+
+# Fill Google credentials
+agent-browser fill @e1 "user@gmail.com"
+agent-browser click @e2  # Next button
+agent-browser wait 2000
+agent-browser snapshot -i
+agent-browser fill @e3 "password"
+agent-browser click @e4  # Sign in
+
+# Wait for redirect back
+agent-browser wait --url "**/app.example.com**"
+agent-browser state save ./oauth-state.json
+```
+
+## Two-Factor Authentication
+
+Handle 2FA with manual intervention:
+
+```bash
+# Login with credentials
+agent-browser open https://app.example.com/login --headed  # Show browser
+agent-browser snapshot -i
+agent-browser fill @e1 "user@example.com"
+agent-browser fill @e2 "password123"
+agent-browser click @e3
+
+# Wait for user to complete 2FA manually
+echo "Complete 2FA in the browser window..."
+agent-browser wait --url "**/dashboard" --timeout 120000
+
+# Save state after 2FA
+agent-browser state save ./2fa-state.json
+```
+
+## HTTP Basic Auth
+
+For sites using HTTP Basic Authentication:
+
+```bash
+# Set credentials before navigation
+agent-browser set credentials username password
+
+# Navigate to protected resource
+agent-browser open https://protected.example.com/api
+```
+
+## Cookie-Based Auth
+
+Manually set authentication cookies:
+
+```bash
+# Set auth cookie
+agent-browser cookies set session_token "abc123xyz"
+
+# Navigate to protected page
+agent-browser open https://app.example.com/dashboard
+```
+
+## Token Refresh Handling
+
+For sessions with expiring tokens:
+
+```bash
+#!/bin/bash
+# Wrapper that handles token refresh
+
+STATE_FILE="./auth-state.json"
+
+# Try loading existing state
+if [[ -f "$STATE_FILE" ]]; then
+    agent-browser state load "$STATE_FILE"
+    agent-browser open https://app.example.com/dashboard
+
+    # Check if session is still valid
+    URL=$(agent-browser get url)
+    if [[ "$URL" == *"/login"* ]]; then
+        echo "Session expired, re-authenticating..."
+        # Perform fresh 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 "$STATE_FILE"
+    fi
+else
+    # First-time login
+    agent-browser open https://app.example.com/login
+    # ... login flow ...
+fi
+```
+
+## Security Best Practices
+
+1. **Never commit state files** - They contain session tokens
+   ```bash
+   echo "*.auth-state.json" >> .gitignore
+   ```
+
+2. **Use environment variables for credentials**
+   ```bash
+   agent-browser fill @e1 "$APP_USERNAME"
+   agent-browser fill @e2 "$APP_PASSWORD"
+   ```
+
+3. **Clean up after automation**
+   ```bash
+   agent-browser cookies clear
+   rm -f ./auth-state.json
+   ```
+
+4. **Use short-lived sessions for CI/CD**
+   ```bash
+   # Don't persist state in CI
+   agent-browser open https://app.example.com/login
+   # ... login and perform actions ...
+   agent-browser close  # Session ends, nothing persisted
+   ```

package/skills/agent-browser/references/proxy-support.md

@@ -0,0 +1,175 @@
+# Proxy Support
+
+Configure proxy servers for browser automation, useful for geo-testing, rate limiting avoidance, and corporate environments.
+
+## Basic Proxy Configuration
+
+Set proxy via environment variable before starting:
+
+```bash
+# HTTP proxy
+export HTTP_PROXY="http://proxy.example.com:8080"
+agent-browser open https://example.com
+
+# HTTPS proxy
+export HTTPS_PROXY="https://proxy.example.com:8080"
+agent-browser open https://example.com
+
+# Both
+export HTTP_PROXY="http://proxy.example.com:8080"
+export HTTPS_PROXY="http://proxy.example.com:8080"
+agent-browser open https://example.com
+```
+
+## Authenticated Proxy
+
+For proxies requiring authentication:
+
+```bash
+# Include credentials in URL
+export HTTP_PROXY="http://username:password@proxy.example.com:8080"
+agent-browser open https://example.com
+```
+
+## SOCKS Proxy
+
+```bash
+# SOCKS5 proxy
+export ALL_PROXY="socks5://proxy.example.com:1080"
+agent-browser open https://example.com
+
+# SOCKS5 with auth
+export ALL_PROXY="socks5://user:pass@proxy.example.com:1080"
+agent-browser open https://example.com
+```
+
+## Proxy Bypass
+
+Skip proxy for specific domains:
+
+```bash
+# Bypass proxy for local addresses
+export NO_PROXY="localhost,127.0.0.1,.internal.company.com"
+agent-browser open https://internal.company.com  # Direct connection
+agent-browser open https://external.com          # Via proxy
+```
+
+## Common Use Cases
+
+### Geo-Location Testing
+
+```bash
+#!/bin/bash
+# Test site from different regions using geo-located proxies
+
+PROXIES=(
+    "http://us-proxy.example.com:8080"
+    "http://eu-proxy.example.com:8080"
+    "http://asia-proxy.example.com:8080"
+)
+
+for proxy in "${PROXIES[@]}"; do
+    export HTTP_PROXY="$proxy"
+    export HTTPS_PROXY="$proxy"
+
+    region=$(echo "$proxy" | grep -oP '^\w+-\w+')
+    echo "Testing from: $region"
+
+    agent-browser --session "$region" open https://example.com
+    agent-browser --session "$region" screenshot "./screenshots/$region.png"
+    agent-browser --session "$region" close
+done
+```
+
+### Rotating Proxies for Scraping
+
+```bash
+#!/bin/bash
+# Rotate through proxy list to avoid rate limiting
+
+PROXY_LIST=(
+    "http://proxy1.example.com:8080"
+    "http://proxy2.example.com:8080"
+    "http://proxy3.example.com:8080"
+)
+
+URLS=(
+    "https://site.com/page1"
+    "https://site.com/page2"
+    "https://site.com/page3"
+)
+
+for i in "${!URLS[@]}"; do
+    proxy_index=$((i % ${#PROXY_LIST[@]}))
+    export HTTP_PROXY="${PROXY_LIST[$proxy_index]}"
+    export HTTPS_PROXY="${PROXY_LIST[$proxy_index]}"
+
+    agent-browser open "${URLS[$i]}"
+    agent-browser get text body > "output-$i.txt"
+    agent-browser close
+
+    sleep 1  # Polite delay
+done
+```
+
+### Corporate Network Access
+
+```bash
+#!/bin/bash
+# Access internal sites via corporate proxy
+
+export HTTP_PROXY="http://corpproxy.company.com:8080"
+export HTTPS_PROXY="http://corpproxy.company.com:8080"
+export NO_PROXY="localhost,127.0.0.1,.company.com"
+
+# External sites go through proxy
+agent-browser open https://external-vendor.com
+
+# Internal sites bypass proxy
+agent-browser open https://intranet.company.com
+```
+
+## Verifying Proxy Connection
+
+```bash
+# Check your apparent IP
+agent-browser open https://httpbin.org/ip
+agent-browser get text body
+# Should show proxy's IP, not your real IP
+```
+
+## Troubleshooting
+
+### Proxy Connection Failed
+
+```bash
+# Test proxy connectivity first
+curl -x http://proxy.example.com:8080 https://httpbin.org/ip
+
+# Check if proxy requires auth
+export HTTP_PROXY="http://user:pass@proxy.example.com:8080"
+```
+
+### SSL/TLS Errors Through Proxy
+
+Some proxies perform SSL inspection. If you encounter certificate errors:
+
+```bash
+# For testing only - not recommended for production
+agent-browser open https://example.com --ignore-https-errors
+```
+
+### Slow Performance
+
+```bash
+# Use proxy only when necessary
+export NO_PROXY="*.cdn.com,*.static.com"  # Direct CDN access
+```
+
+## Best Practices
+
+1. **Use environment variables** - Don't hardcode proxy credentials
+2. **Set NO_PROXY appropriately** - Avoid routing local traffic through proxy
+3. **Test proxy before automation** - Verify connectivity with simple requests
+4. **Handle proxy failures gracefully** - Implement retry logic for unstable proxies
+5. **Rotate proxies for large scraping jobs** - Distribute load and avoid bans