Agent skill · software engineering · sundial-org
agent-browser-5
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Why this skill is useful
Provides specific commands and workflows for headless browser automation that the AI wouldn't reliably generate on its own.
What it needs
Requires node, npm installed locally. About 5k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Browser Automation with agent-browser Installation npm recommended From Source Quick start 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 Snapshot (page analysis) Interactions (use @refs from snapshot) Get information Check state Screenshots & PDF Video 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 Mouse control Semantic locators (alternative to refs) Browser settings Cookies & Storage Network Tabs & Windows Frames Dialogs JavaScript State management Example: Form submission Example: Authentication with saved state Sessions (parallel browsers) JSON output (for parsing) Add --json for machine-readable output: Debugging Troubleshooting If the command is not found on Linux ARM64, use the full path in the bin folder. If an element is not found, use snapshot to find the correct ref. If the page is not loaded, add a wait command after navigation. Use --headed to see the browser window for debugging. Options --session <name> uses an isolated session. --json provides JSON output. --full takes a full page screenshot. --headed shows the browser window. --timeout sets the command timeout in milliseconds. --cdp <port> connects via Chrome DevTools Protocol. Notes Refs are stable per page load but change on navigation. Always snapshot after navigation to get new refs. Use fill instead of type for input fields to ensure existing text is cleared. Reporting Issues Skill issues: Open an issue at https://github.com/TheSethRose/Agent-Browser-CLI agent-browser CLI issues: Open an issue at https://github.com/vercel-labs/agent-browser
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/agent-browser-5