← ClaudeAtlas

browserlisted

Use when building browser automation scripts that need to control Chrome via the AgentInBrowser REST API. Covers how to start/stop the server, send commands, and handle responses.
xjsongphy/skills · ★ 6 · AI & Automation · score 68
Install: claude install-skill xjsongphy/skills
# AgentInBrowser Skill ## Overview AgentInBrowser is a REST API service that provides remote control of a Chrome browser. It wraps Selenium WebDriver and exposes HTTP endpoints for browser operations (find elements, click, type, screenshot, execute JS, etc.). **Project Location**: `D:\Develop\AgentInBrowser` ## When to Use - Building browser automation scripts (auto-login, course watching, form filling, etc.) - Need to control browser via HTTP interface instead of using Selenium directly - Need to run browser tasks in background without detection ## Quick Reference ### Start Server ```bash # In project directory (using uv) cd D:\Develop\AgentInBrowser source .venv/bin/activate # Linux/macOS # or .venv\Scripts\activate # Windows aib # Or use directly after global install aib ``` Server listens on: `http://127.0.0.1:5000` ### Check Server Status ```python import requests resp = requests.get("http://127.0.0.1:5000/status") # → {"status": "running", "browser_active": false, "current_url": null} ``` ### Stop Server ```python requests.post("http://127.0.0.1:5000/shutdown") # Close browser + exit server requests.post("http://127.0.0.1:5000/quit") # Close browser only, server stays alive ``` ## API Endpoints | Endpoint | Method | Description | |----------|--------|-------------| | `/status` | GET | Get server status | | `/env` | GET | Get server environment info (project dir, venv path, etc.) | | `/init` | POST | Initialize browser and navigate to URL | | `/ex