Agent Browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...

Security Scan

The skill's docs look like a legitimate browser-automation helper, but the package metadata omits key runtime requirements and the runtime instructions reference sensitive environment variables, saved state files, arbitrary JS eval, and proxy/network controls — these mismatches and broad capabilities deserve caution before installing.

Purpose & Capability

The skill's name and description match the included templates and documentation: it is clearly a browser-automation CLI helper. However the registry metadata claims no required binaries or env vars, while SKILL.md and the templates repeatedly call an external CLI named `agent-browser` and demonstrate/require environment variables (e.g., APP_USERNAME, APP_PASSWORD, AGENT_BROWSER_ENCRYPTION_KEY, AGENT_BROWSER_*) and state file locations (~/.agent-browser/sessions/, ./auth-state.json). The omission of the primary runtime dependency (the agent-browser binary) from metadata is an incoherence: either the binary is expected to already exist on the host, or the metadata is incomplete.

Instruction Scope

The runtime instructions and templates instruct the agent to read and write local state files (session/state JSONs), load/save authentication state, access environment variables for credentials and encryption keys, configure proxies (including proxied credentials), and execute arbitrary JavaScript via `agent-browser eval --stdin` or base64-encoded scripts. These actions go beyond simple read-only browsing: they persist sensitive tokens to disk, may require credential environment variables, and allow arbitrary JS to run in page contexts (a capable avenue for data extraction/exfiltration if misused). While these operations are coherent with a browser automation tool, the SKILL.md grants broad discretion (e.g., use of proxies and base64 JS) and references env vars that are not declared in the skill's required env list.

Install Mechanism

There is no install specification (instruction-only), and the repository contains only documentation and shell templates. That is lower risk from an installer perspective because nothing in the skill package will automatically download and execute code. However the templates assume an external CLI (`agent-browser`) is present and will be invoked; the skill does not provide or declare how that binary is installed. You should confirm where `agent-browser` comes from and inspect/trust that binary before running templates.

Credentials

The skill metadata lists no required environment variables, but the SKILL.md and templates make repeated use of environment variables for credentials (APP_USERNAME, APP_PASSWORD), encryption keys (AGENT_BROWSER_ENCRYPTION_KEY), and proxy variables (HTTP_PROXY/HTTPS_PROXY/ALL_PROXY). Those are sensitive by nature (passwords, session tokens, proxy creds) and they are used to persist state files that 'contain session tokens'. The skill does not declare these as required, nor does it limit how/where state is stored. This mismatch reduces transparency about what secrets the skill will touch.

Persistence & Privilege

The skill does not request special platform privileges (always:false). It explicitly instructs saving and loading session state files (cookies/localStorage/indexedDB) to disk and storing sessions under ~/.agent-browser/sessions or user-specified files. Persisting browser auth state locally is expected for this class of tool, but these files contain credentials/session tokens and must be handled carefully (the docs themselves warn against committing them). The skill does not attempt to modify other skills or global agent settings.

What to consider before installing

This skill appears to implement a real browser-automation workflow, but there are important mismatches and risks to consider before installing or running it: - Confirm the `agent-browser` CLI: SKILL.md and templates repeatedly invoke an external `agent-browser` command, but the package metadata does not declare that binary or an install path. Ask the publisher where that binary comes from and inspect/trust it before running any templates. - Sensitive env vars and state files: the docs reference APP_USERNAME, APP_PASSWORD, AGENT_BROWSER_ENCRYPTION_KEY, and proxy credentials. The templates save session files that contain cookies/storage (they can include auth tokens). Do not run templates with real credentials until you understand where state files are written and how they are protected; avoid committing state files to source control. - Arbitrary JS execution: the tool supports running arbitrary JavaScript in pages (base64 or stdin). That is useful for scraping or testing but can be used to extract secrets displayed in the page context. Only run JS you understand, and review any automation scripts that use `eval`/`--stdin`. - Network/proxy controls: the skill encourages using proxies and rotating proxies for scraping. These features enable behaviors that may violate target sites' terms of service or be used for large-scale scraping. Ensure you have appropriate authorization and comply with laws/policies. - Minimal install surface here: because this is instruction-only, the repository itself doesn't install code, but templates will call an external CLI. Inspect and vet that CLI and any provider binaries before use. Recommendations: 1) Ask the publisher for the source and install instructions for the `agent-browser` binary and verify its authenticity. 2) If you plan to use saved session files, configure and use encryption keys and delete them when done; follow the docs' 'never commit state files' advice. 3) Prefer ephemeral credentials for automation and use short-lived accounts for CI/testing. 4) Review any automation scripts (especially those using eval or proxies) for unintended data exfiltration. If the publisher cannot explain where `agent-browser` is obtained or why the metadata omits the runtime dependencies and expected env vars, treat installation as higher risk.

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

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "[e-mail]" && agent-browser fill @e2 "password123" && agent-browser click @e3

# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).

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 -i -C          # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser click @e1 --new-tab     # Click and open in new tab
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 screenshot --annotate   # Annotated screenshot with numbered element labels
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 "[e-mail]"
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

Session Persistence

# Auto-save/restore cookies and localStorage across browser restarts
agent-browser --session-name myapp open https://app.example.com/login
# ... login flow ...
agent-browser close  # State auto-saved to ~/.agent-browser/sessions/

# Next time, state is auto-loaded
agent-browser --session-name myapp open https://app.example.com/dashboard

# Encrypt state at rest
export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32)
agent-browser --session-name secure open https://app.example.com

# Manage saved states
agent-browser state list
agent-browser state show myapp-default.json
agent-browser state clear myapp
agent-browser state clean --older-than 7

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

Connect to Existing Chrome

# Auto-discover running Chrome with remote debugging enabled
agent-browser --auto-connect open https://example.com
agent-browser --auto-connect snapshot

# Or with explicit CDP port
agent-browser --cdp 9222 snapshot

Visual Browser (Debugging)

agent-browser --headed open https://example.com
agent-browser highlight @e1          # Highlight element
agent-browser record start demo.webm # Record session
agent-browser profiler start         # Start Chrome DevTools profiling
agent-browser profiler stop trace.json # Stop and save profile (path optional)

Local Files (PDFs, HTML)

# Open local files with file:// URLs
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

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.

Timeouts and Slow Pages

The default Playwright timeout is 60 seconds for local browsers. For slow websites or large pages, use explicit waits instead of relying on the default timeout:

# Wait for network activity to settle (best for slow pages)
agent-browser wait --load networkidle

# Wait for a specific element to appear
agent-browser wait "#content"
agent-browser wait @e1

# Wait for a specific URL pattern (useful after redirects)
agent-browser wait --url "**/dashboard"

# Wait for a JavaScript condition
agent-browser wait --fn "document.readyState === 'complete'"

# Wait a fixed duration (milliseconds) as a last resort
agent-browser wait 5000

When dealing with consistently slow websites, use wait --load networkidle after open to ensure the page is fully loaded before taking a snapshot. If a specific element is slow to render, wait for it directly with wait <selector> or wait @ref.

Session Management and Cleanup

When running multiple agents or automations concurrently, always use named sessions to avoid conflicts:

# Each agent gets its own isolated session
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

# Check active sessions
agent-browser session list

Always close your browser session when done to avoid leaked processes:

agent-browser close                    # Close default session
agent-browser --session agent1 close   # Close specific session

If a previous session was not closed properly, the daemon may still be running. Use agent-browser close to clean it up before starting new work.

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

Annotated Screenshots (Vision Mode)

Use --annotate to take a screenshot with numbered labels overlaid on interactive elements. Each label [N] maps to ref @eN. This also caches refs, so you can interact with elements immediately without a separate snapshot.

agent-browser screenshot --annotate
# Output includes the image path and a legend:
#   [1] @e1 button "Submit"
#   [2] @e2 link "Home"
#   [3] @e3 textbox "Email"
agent-browser click @e2              # Click using ref from annotated screenshot

Use annotated screenshots when:

• The page has unlabeled icon buttons or visual-only elements
• You need to verify visual layout or styling
• Canvas or chart elements are present (invisible to text snapshots)
• You need spatial reasoning about element positions

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 "[e-mail]"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click

JavaScript Evaluation (eval)

Use eval to run JavaScript in the browser context. Shell quoting can corrupt complex expressions -- use --stdin or -b to avoid issues.

# Simple expressions work with regular quoting
agent-browser eval 'document.title'
agent-browser eval 'document.querySelectorAll("img").length'

# Complex JS: use --stdin with heredoc (RECOMMENDED)
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("img"))
    .filter(i => !i.alt)
    .map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF

# Alternative: base64 encoding (avoids all shell escaping issues)
agent-browser eval -b "$(echo -n 'Array.from(document.querySelectorAll("a")).map(a => a.href)' | base64)"

Why this matters: When the shell processes your command, inner double quotes, ! characters (history expansion), backticks, and $() can all corrupt the JavaScript before it reaches agent-browser. The --stdin and -b flags bypass shell interpretation entirely.

Rules of thumb:

• Single-line, no nested quotes -> regular eval 'expression' with single quotes is fine
• Nested quotes, arrow functions, template literals, or multiline -> use eval --stdin <<'EVALEOF'
• Programmatic/generated scripts -> use eval -b with base64

Configuration File

Create agent-browser.json in the project root for persistent settings:

{
  "headed": true,
  "proxy": "http://localhost:8080",
  "profile": "./browser-data"
}

Priority (lowest to highest): ~/.agent-browser/config.json < ./agent-browser.json < env vars < CLI flags. Use --config <path> or AGENT_BROWSER_CONFIG env var for a custom config file (exits with error if missing/invalid). All CLI options map to camelCase keys (e.g., --executable-path -> "executablePath"). Boolean flags accept true/false values (e.g., --headed false overrides config). Extensions from user and project configs are merged, not replaced.

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/profiling.md	Chrome DevTools profiling for performance analysis
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