This is a headless browser CLI built in Rust with a Node.js fallback that gives Claude structured web automation commands. You get snapshot, click, fill, and type commands that work with element references like @e1, @e2 instead of writing selectors. The workflow is straightforward: open a URL, snapshot to get interactive elements with refs, then use those refs to click buttons or fill forms. It includes video recording for demos, state management to save login sessions, and network interception for mocking APIs. The ref-based approach is cleaner than wrestling with CSS selectors when you need to automate forms, scrape data, or test UIs programmatically.

skills.sh installs
129
GitHub stars
674
last updated
Aug 21, 2026

Install

$ npx -y skills add sundial-org/awesome-openclaw-skills --skill agent-browser --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser Automation with agent-browser

Installation

npm recommended

npm install -g agent-browser
agent-browser install
agent-browser install --with-deps

From Source

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
  3. Interact using refs from the snapshot
  4. Re-snapshot after navigation or significant DOM changes

Commands

Navigation

agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Snapshot (page analysis)

Sponsors

Details

Repository
github.com/sundial-org/awesome-openclaw-skills
Categories
Testing & QA, AI & Agent Building, Automation & Workflows, Rust, CLI & Terminal
First seen
Jun 3, 2026

More from sundial-org/awesome-openclaw-skills

All 39
1cherryhq avatarskill-creatorcherryhq/cherry-studioCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an e0skills.sh installs
2composiohq avatarperf-theory-testercomposiohq/awesome-claude-pluginsThis is for when you're doing performance testing and need to stay disciplined about changing one variable at a time.0skills.sh installs
3countbot-ai avatarskill-creatorcountbot-ai/countbotCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an e0skills.sh installs
4daffy0208 avatarQuality Assurancedaffy0208/ai-dev-standardsComprehensive quality assurance combining testing strategy, code quality enforcement, and validation gates. Consolidated from testing-strategist, code-quality-e0skills.sh installs
5davila7 avatarPentest Commandsdavila7/claude-code-templatesThis skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan0skills.sh installs
6getsentry avatarpackgetsentry/sentry-unrealPackage plugin and update file snapshot0skills.sh installs