agent-browser

Automates browser interactions via a CLI using Chrome DevTools Protocol and accessibility-tree snapshots.

1|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/rockcookies/skills --skill agent-browser-rockcookies
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/rockcookies/skills/tree/main/skills/vercel-agent-browser/agent-browser
Command: npx skills add https://github.com/rockcookies/skills --skill agent-browser-rockcookies

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? AI agents lack a reliable way to interact with live websites—navigating pages, filling forms, clicking buttons, and extracting data typically require brittle custom scripts or heavyweight frameworks. This Skill provides a fast CLI that drives Chrome/Chromium over CDP with accessibility-tree snapshots and stable element references. ## Core Features & Use Cases - Browser Automation: Navigate pages, fill forms, click buttons, take screenshots, and scrape data using compact @eN element refs from accessibility-tree snapshots. - Specialized Targets: Automate Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspaces, exploratory QA/dogfooding sessions, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Session & Observability: Manage sessions, authentication vaults, state persistence, video recording, and an observability dashboard on port 4848. - Use Case: Ask the agent to log into a staging web app, walk through the checkout flow, capture screenshots of each step, and report any broken UI elements found during exploratory testing. ## Quick Start Install the CLI with npm, run agent-browser install, then ask the agent to load the core workflow with agent-browser skills get core before automating any website.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks with an AI agent?▼

Install the agent-browser CLI globally with npm, run agent-browser install, then load workflow instructions via agent-browser skills get core. The CLI drives Chrome/Chromium over CDP and exposes accessibility-tree snapshots with element refs for reliable interaction.

What browser automation tool works without Playwright or Puppeteer?▼

agent-browser is a native Rust CLI that controls Chrome/Chromium directly through the Chrome DevTools Protocol, with no Playwright or Puppeteer dependency. It provides accessibility-tree snapshots and compact @eN element references for interactions.

Can agent-browser automate Electron desktop apps like Slack or VS Code?▼

Yes, agent-browser supports Electron desktop apps including VS Code, Slack, Discord, Figma, Notion, and Spotify. Load the dedicated instructions with agent-browser skills get electron before automating those applications.

Does agent-browser support cloud browsers and sandboxed environments?▼

Yes, it supports running inside Vercel Sandbox microVMs and AWS Bedrock AgentCore cloud browsers. Load the corresponding guidance with agent-browser skills get vercel-sandbox or agent-browser skills get agentcore.

How do I check Slack messages with browser automation?▼

Load the Slack-specific workflow with agent-browser skills get slack. It covers checking unread messages, sending messages, and searching conversations in a Slack workspace through the automated browser session.