agent browser Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. agent browser is a headless browser automation CLI built in Rust, designed for AI agents. It wraps Chrome via the Chrome DevTools Protocol (CDP) and exposes a fast, ergonomic command line interface for navigation, interaction, accessibility snapshots, screenshots, network interception, and more — with no Node.js or Playwright runtime required. Installation Recommended (npm global) macOS (Homebrew) Rust / Cargo Local project dependency Linux (with system dependencies) Quick Start Core Commands Navigation Accessibility Snapshot (recommended for AI agents) Snapshot output includes @eN refs you can use directly: Then act on them: Interaction Screenshots & PDF Getting Element Info State Checks Semantic Locators (find) Actions: click , fill , type , hover , focus , check , uncheck , text Waiting Load states: load , domcontentloaded , networkidle JavaScript Eval Batch Execution (efficient multi step) Tabs & Frames Cookies & Storage Network Browser Settings Auth State Dialogs Clipboard Diff & Visual Testing Debug & Profiling Common Patterns Login flow and save session AI agent loop with snapshot driven interaction Batch commands from a script (JSON) Scrape with mocked network Full page screenshot with annotations Connect to already running Chrome Emulate mobile device HAR recording for network analysis Selector Reference Format Example Notes @ref @e1 , @e12 From snapshot output — preferred for AI CSS id , .class , [attr=val] Standard CSS selectors Text "Sign In" Exact text match XPath //button[@type='submit'] Full XPath Troubleshooting Chrome not found Element not found / timing issues Selector issues — use snapshot refs instead Debug what's on the page Auth issues between sessions Handling alerts/dialogs Performance — use batch for multi step workflows

agent-browser-automation