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 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.
Best use case
agent-browser is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using agent-browser should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-browser/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-browser Compares
| Feature / Agent | agent-browser | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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 ```bash 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 ```bash # 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 ```bash 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 ```bash # 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 ```bash 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 ```bash 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) ```bash 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) ```bash # 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) ```bash 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: ```bash 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](references/commands.md) | Full command reference with all options | | [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 | 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 | ```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 ```
Related Skills
headless-ui
Use @momentumcms/headless inside generated Momentum apps. Use when building custom public UI, composing accessible primitives, configuring global styles for hdl-* elements, or adding app-level tests around headless interactions.
ui-audit
Comprehensive UI component audit for Momentum CMS. Use when asked to audit, review, check, or validate a UI component. Checks Storybook stories, interaction tests, variants, kitchen sink integration, admin dashboard usage, accessibility, and responsive design (mobile-first). AUTOMATICALLY FIXES issues found and verifies with visual inspection. Triggers include "audit button", "review the card component", "check accessibility of tabs", or "/ui-audit <component-name>".
test-all
Run the FULL Momentum CMS test suite — every single suite, no skips. Triggers on "test all", "test everything", "run all tests", "run the test all script", "test-all script", "run the full suite", "run every test", "test the whole thing", "make sure everything passes", "run test:all", or ANY variation asking to run all/every/full tests. Also triggers on typos like "test al", "tets all", "tes all". NEVER skip suites unless the user EXPLICITLY names suites to skip.
stroll-test
End-to-end CLI stroll test of npm-published Momentum CMS packages. Scaffolds a fresh project with create-momentum-app, adds all plugins, runs migrations, starts server, and verifies everything works. Triggers include "stroll test", "cli stroll", "test published packages", or "/stroll-test".
skill-improve
Self-improving skill loop. Analyzes eval failures, rewrites the skill, re-evaluates, and repeats until convergence. Run after /skill-eval produces baseline results.
skill-eval
Run structured evaluations comparing skill vs no-skill performance. Measures assertion pass rates, timing, and output quality to systematically improve skills.
prepare-release
Prepare a patch/minor/major version release for all Momentum CMS packages. Bumps versions, generates changelogs, verifies builds/tests, adds new packages to Nx release config, and commits. Triggers include "prepare release", "bump version", "release patch", or "/prepare-release".
momentum-api
Work with Momentum API for data operations in Angular components
migrations
Run migrations, generate schemas, and manage code generation for Momentum CMS. Use when working with database migrations, Drizzle schema generation, type generation, or Angular schematics.
mcp-setup
Set up the Momentum CMS MCP server plugin and generate Claude Code MCP config for AI tool integration. Use when connecting Claude Code (or any MCP client) to a Momentum CMS instance.
SYSTEM ROLE & BEHAVIORAL PROTOCOLS
**ROLE:** Senior Frontend Architect & Avant-Garde UI Designer.
headless-primitive
Author, extend, or repair primitives in libs/headless. Use when adding a new headless primitive, changing its accessibility contract, updating slots/state attrs, wiring overlay behavior, or expanding the example styling lab and tests.