agent-browser 0.8.7 → 0.8.10

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

@@ -0,0 +1,259 @@
+# Command Reference
+
+Complete reference for all agent-browser commands. For quick start and common patterns, see SKILL.md.
+
+## Navigation
+
+```bash
+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 (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)
+agent-browser snapshot -c         # Compact output
+agent-browser snapshot -d 3       # Limit depth to 3
+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 (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 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
+agent-browser get value @e1       # Get input value
+agent-browser get attr @e1 href   # Get attribute
+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
+agent-browser is checked @e1      # Check if checked
+```
+
+## Screenshots and PDF
+
+```bash
+agent-browser screenshot          # Save to temporary directory
+agent-browser screenshot path.png # Save to specific path
+agent-browser screenshot --full   # Full page
+agent-browser pdf output.pdf      # Save as PDF
+```
+
+## Video Recording
+
+```bash
+agent-browser record start ./demo.webm    # Start recording
+agent-browser click @e1                   # Perform actions
+agent-browser record stop                 # Stop and save video
+agent-browser record restart ./take2.webm # Stop current + start new
+```
+
+## Wait
+
+```bash
+agent-browser wait @e1                     # Wait for element
+agent-browser wait 2000                    # Wait milliseconds
+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
+agent-browser mouse up left           # Release button
+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 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 (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 and Storage
+
+```bash
+agent-browser cookies                     # Get all cookies
+agent-browser cookies set name value      # Set cookie
+agent-browser cookies clear               # Clear cookies
+agent-browser storage local               # Get all localStorage
+agent-browser storage local key           # Get specific key
+agent-browser storage local set k v       # Set value
+agent-browser storage local clear         # Clear all
+```
+
+## Network
+
+```bash
+agent-browser network route <url>              # Intercept requests
+agent-browser network route <url> --abort      # Block requests
+agent-browser network route <url> --body '{}'  # Mock response
+agent-browser network unroute [url]            # Remove routes
+agent-browser network requests                 # View tracked requests
+agent-browser network requests --filter api    # Filter requests
+```
+
+## Tabs and Windows
+
+```bash
+agent-browser tab                 # List tabs
+agent-browser tab new [url]       # New 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"          # Simple expressions only
+agent-browser eval -b "<base64>"             # Any JavaScript (base64 encoded)
+agent-browser eval --stdin                   # Read script from stdin
+```
+
+Use `-b`/`--base64` or `--stdin` for reliable execution. Shell escaping with nested quotes and special characters is error-prone.
+
+```bash
+# Base64 encode your script, then:
+agent-browser eval -b "ZG9jdW1lbnQucXVlcnlTZWxlY3RvcignW3NyYyo9Il9uZXh0Il0nKQ=="
+
+# Or use stdin with heredoc for multiline scripts:
+cat <<'EOF' | agent-browser eval --stdin
+const links = document.querySelectorAll('a');
+Array.from(links).map(a => a.href);
+EOF
+```
+
+## State Management
+
+```bash
+agent-browser state save auth.json    # Save cookies, storage, auth state
+agent-browser state load auth.json    # Restore saved state
+```
+
+## 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 --ignore-https-errors   # Ignore SSL certificate errors
+agent-browser --help                  # Show help (-h)
+agent-browser --version               # Show version (-V)
+agent-browser <command> --help        # Show detailed help for a command
+```
+
+## Debugging
+
+```bash
+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
+```
+
+## 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
+```

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

@@ -1,6 +1,19 @@
 # Proxy Support
 
-Configure proxy servers for browser automation, useful for geo-testing, rate limiting avoidance, and corporate environments.
+Proxy configuration for geo-testing, rate limiting avoidance, and corporate environments.
+
+**Related**: [commands.md](commands.md) for global options, [SKILL.md](../SKILL.md) for quick start.
+
+## Contents
+
+- [Basic Proxy Configuration](#basic-proxy-configuration)
+- [Authenticated Proxy](#authenticated-proxy)
+- [SOCKS Proxy](#socks-proxy)
+- [Proxy Bypass](#proxy-bypass)
+- [Common Use Cases](#common-use-cases)
+- [Verifying Proxy Connection](#verifying-proxy-connection)
+- [Troubleshooting](#troubleshooting)
+- [Best Practices](#best-practices)
 
 ## Basic Proxy Configuration
 

package/skills/agent-browser/references/session-management.md

@@ -1,6 +1,18 @@
 # Session Management
 
-Run multiple isolated browser sessions concurrently with state persistence.
+Multiple isolated browser sessions with state persistence and concurrent browsing.
+
+**Related**: [authentication.md](authentication.md) for login patterns, [SKILL.md](../SKILL.md) for quick start.
+
+## Contents
+
+- [Named Sessions](#named-sessions)
+- [Session Isolation Properties](#session-isolation-properties)
+- [Session State Persistence](#session-state-persistence)
+- [Common Patterns](#common-patterns)
+- [Default Session](#default-session)
+- [Session Cleanup](#session-cleanup)
+- [Best Practices](#best-practices)
 
 ## Named Sessions
 

package/skills/agent-browser/references/snapshot-refs.md

@@ -1,21 +1,29 @@
-# Snapshot + Refs Workflow
+# Snapshot and Refs
 
-The core innovation of agent-browser: compact element references that reduce context usage dramatically for AI agents.
+Compact element references that reduce context usage dramatically for AI agents.
 
-## How It Works
+**Related**: [commands.md](commands.md) for full command reference, [SKILL.md](../SKILL.md) for quick start.
 
-### The Problem
-Traditional browser automation sends full DOM to AI agents:
+## Contents
+
+- [How Refs Work](#how-refs-work)
+- [Snapshot Command](#the-snapshot-command)
+- [Using Refs](#using-refs)
+- [Ref Lifecycle](#ref-lifecycle)
+- [Best Practices](#best-practices)
+- [Ref Notation Details](#ref-notation-details)
+- [Troubleshooting](#troubleshooting)
+
+## How Refs Work
+
+Traditional approach:
 ```
-Full DOM/HTML sent → AI parses → Generates CSS selector → Executes action
-~3000-5000 tokens per interaction
+Full DOM/HTML → AI parses → CSS selector → Action (~3000-5000 tokens)
 ```
 
-### The Solution
-agent-browser uses compact snapshots with refs:
+agent-browser approach:
 ```
-Compact snapshot → @refs assigned → Direct ref interaction
-~200-400 tokens per interaction
+Compact snapshot → @refs assigned → Direct interaction (~200-400 tokens)
 ```
 
 ## The Snapshot Command

package/skills/agent-browser/references/video-recording.md

@@ -1,6 +1,17 @@
 # Video Recording
 
-Capture browser automation sessions as video for debugging, documentation, or verification.
+Capture browser automation as video for debugging, documentation, or verification.
+
+**Related**: [commands.md](commands.md) for full command reference, [SKILL.md](../SKILL.md) for quick start.
+
+## Contents
+
+- [Basic Recording](#basic-recording)
+- [Recording Commands](#recording-commands)
+- [Use Cases](#use-cases)
+- [Best Practices](#best-practices)
+- [Output Format](#output-format)
+- [Limitations](#limitations)
 
 ## Basic Recording
 

package/skills/agent-browser/templates/authenticated-session.sh

@@ -1,34 +1,41 @@
 #!/bin/bash
 # Template: Authenticated Session Workflow
-# Login once, save state, reuse for subsequent runs
+# Purpose: Login once, save state, reuse for subsequent runs
+# Usage: ./authenticated-session.sh <login-url> [state-file]
 #
-# Usage:
-#   ./authenticated-session.sh <login-url> [state-file]
+# Environment variables:
+#   APP_USERNAME - Login username/email
+#   APP_PASSWORD - Login password
 #
-# Setup:
-#   1. Run once to see your form structure
-#   2. Note the @refs for your fields
-#   3. Uncomment LOGIN FLOW section and update refs
+# Two modes:
+#   1. Discovery mode (default): Shows form structure so you can identify refs
+#   2. Login mode: Performs actual login after you update the refs
+#
+# Setup steps:
+#   1. Run once to see form structure (discovery mode)
+#   2. Update refs in LOGIN FLOW section below
+#   3. Set APP_USERNAME and APP_PASSWORD
+#   4. Delete the DISCOVERY section
 
 set -euo pipefail
 
 LOGIN_URL="${1:?Usage: $0 <login-url> [state-file]}"
 STATE_FILE="${2:-./auth-state.json}"
 
-echo "Authentication workflow for: $LOGIN_URL"
+echo "Authentication workflow: $LOGIN_URL"
 
-# ══════════════════════════════════════════════════════════════
-# SAVED STATE: Skip login if we have valid saved state
-# ══════════════════════════════════════════════════════════════
+# ================================================================
+# SAVED STATE: Skip login if valid saved state exists
+# ================================================================
 if [[ -f "$STATE_FILE" ]]; then
-    echo "Loading saved authentication state..."
+    echo "Loading saved state from $STATE_FILE..."
     agent-browser state load "$STATE_FILE"
     agent-browser open "$LOGIN_URL"
     agent-browser wait --load networkidle
 
     CURRENT_URL=$(agent-browser get url)
     if [[ "$CURRENT_URL" != *"login"* ]] && [[ "$CURRENT_URL" != *"signin"* ]]; then
-        echo "Session restored successfully!"
+        echo "Session restored successfully"
         agent-browser snapshot -i
         exit 0
     fi
@@ -36,32 +43,31 @@ if [[ -f "$STATE_FILE" ]]; then
     rm -f "$STATE_FILE"
 fi
 
-# ══════════════════════════════════════════════════════════════
-# DISCOVERY MODE: Show form structure (remove after setup)
-# ══════════════════════════════════════════════════════════════
+# ================================================================
+# DISCOVERY MODE: Shows form structure (delete after setup)
+# ================================================================
 echo "Opening login page..."
 agent-browser open "$LOGIN_URL"
 agent-browser wait --load networkidle
 
 echo ""
-echo "┌─────────────────────────────────────────────────────────┐"
-echo "│ LOGIN FORM STRUCTURE                                    │"
-echo "├─────────────────────────────────────────────────────────┤"
+echo "Login form structure:"
+echo "---"
 agent-browser snapshot -i
-echo "└─────────────────────────────────────────────────────────┘"
+echo "---"
 echo ""
 echo "Next steps:"
-echo "  1. Note refs: @e? = username, @e? = password, @e? = submit"
-echo "  2. Uncomment LOGIN FLOW section below"
-echo "  3. Replace @e1, @e2, @e3 with your refs"
+echo "  1. Note the refs: username=@e?, password=@e?, submit=@e?"
+echo "  2. Update the LOGIN FLOW section below with your refs"
+echo "  3. Set: export APP_USERNAME='...' APP_PASSWORD='...'"
 echo "  4. Delete this DISCOVERY MODE section"
 echo ""
 agent-browser close
 exit 0
 
-# ══════════════════════════════════════════════════════════════
+# ================================================================
 # LOGIN FLOW: Uncomment and customize after discovery
-# ══════════════════════════════════════════════════════════════
+# ================================================================
 # : "${APP_USERNAME:?Set APP_USERNAME environment variable}"
 # : "${APP_PASSWORD:?Set APP_PASSWORD environment variable}"
 #
@@ -78,14 +84,14 @@ exit 0
 # # Verify login succeeded
 # FINAL_URL=$(agent-browser get url)
 # if [[ "$FINAL_URL" == *"login"* ]] || [[ "$FINAL_URL" == *"signin"* ]]; then
-#     echo "ERROR: Login failed - still on login page"
+#     echo "Login failed - still on login page"
 #     agent-browser screenshot /tmp/login-failed.png
 #     agent-browser close
 #     exit 1
 # fi
 #
 # # Save state for future runs
-# echo "Saving authentication state to: $STATE_FILE"
+# echo "Saving state to $STATE_FILE"
 # agent-browser state save "$STATE_FILE"
-# echo "Login successful!"
+# echo "Login successful"
 # agent-browser snapshot -i

package/skills/agent-browser/templates/capture-workflow.sh

@@ -1,68 +1,69 @@
 #!/bin/bash
 # Template: Content Capture Workflow
-# Extract content from web pages with optional authentication
+# Purpose: Extract content from web pages (text, screenshots, PDF)
+# Usage: ./capture-workflow.sh <url> [output-dir]
+#
+# Outputs:
+#   - page-full.png: Full page screenshot
+#   - page-structure.txt: Page element structure with refs
+#   - page-text.txt: All text content
+#   - page.pdf: PDF version
+#
+# Optional: Load auth state for protected pages
 
 set -euo pipefail
 
 TARGET_URL="${1:?Usage: $0 <url> [output-dir]}"
 OUTPUT_DIR="${2:-.}"
 
-echo "Capturing content from: $TARGET_URL"
+echo "Capturing: $TARGET_URL"
 mkdir -p "$OUTPUT_DIR"
 
-# Optional: Load authentication state if needed
+# Optional: Load authentication state
 # if [[ -f "./auth-state.json" ]]; then
+#     echo "Loading authentication state..."
 #     agent-browser state load "./auth-state.json"
 # fi
 
-# Navigate to target page
+# Navigate to target
 agent-browser open "$TARGET_URL"
 agent-browser wait --load networkidle
 
-# Get page metadata
-echo "Page title: $(agent-browser get title)"
-echo "Page URL: $(agent-browser get url)"
+# Get metadata
+TITLE=$(agent-browser get title)
+URL=$(agent-browser get url)
+echo "Title: $TITLE"
+echo "URL: $URL"
 
 # Capture full page screenshot
 agent-browser screenshot --full "$OUTPUT_DIR/page-full.png"
-echo "Screenshot saved: $OUTPUT_DIR/page-full.png"
+echo "Saved: $OUTPUT_DIR/page-full.png"
 
-# Get page structure
+# Get page structure with refs
 agent-browser snapshot -i > "$OUTPUT_DIR/page-structure.txt"
-echo "Structure saved: $OUTPUT_DIR/page-structure.txt"
+echo "Saved: $OUTPUT_DIR/page-structure.txt"
 
-# Extract main content
-# Adjust selector based on target site structure
-# agent-browser get text @e1 > "$OUTPUT_DIR/main-content.txt"
-
-# Extract specific elements (uncomment as needed)
-# agent-browser get text "article" > "$OUTPUT_DIR/article.txt"
-# agent-browser get text "main" > "$OUTPUT_DIR/main.txt"
-# agent-browser get text ".content" > "$OUTPUT_DIR/content.txt"
-
-# Get full page text
+# Extract all text content
 agent-browser get text body > "$OUTPUT_DIR/page-text.txt"
-echo "Text content saved: $OUTPUT_DIR/page-text.txt"
+echo "Saved: $OUTPUT_DIR/page-text.txt"
 
-# Optional: Save as PDF
+# Save as PDF
 agent-browser pdf "$OUTPUT_DIR/page.pdf"
-echo "PDF saved: $OUTPUT_DIR/page.pdf"
+echo "Saved: $OUTPUT_DIR/page.pdf"
+
+# Optional: Extract specific elements using refs from structure
+# agent-browser get text @e5 > "$OUTPUT_DIR/main-content.txt"
 
-# Optional: Capture with scrolling for infinite scroll pages
-# scroll_and_capture() {
-#     local count=0
-#     while [[ $count -lt 5 ]]; do
-#         agent-browser scroll down 1000
-#         agent-browser wait 1000
-#         ((count++))
-#     done
-#     agent-browser screenshot --full "$OUTPUT_DIR/page-scrolled.png"
-# }
-# scroll_and_capture
+# Optional: Handle infinite scroll pages
+# for i in {1..5}; do
+#     agent-browser scroll down 1000
+#     agent-browser wait 1000
+# done
+# agent-browser screenshot --full "$OUTPUT_DIR/page-scrolled.png"
 
 # Cleanup
 agent-browser close
 
 echo ""
-echo "Capture complete! Files saved to: $OUTPUT_DIR"
+echo "Capture complete:"
 ls -la "$OUTPUT_DIR"