agent-browser

vercel-labs/agent-browser · Agent Skill

Browser automation CLI for AI agents for navigation, form actions, extraction, screenshots, QA, and app testing.

Overview

Publisher	vercel-labsOrganization
Repository	vercel-labs/agent-browser ↗
Skill folder	`agent-browser`
Stars	44,631
Forks	3,060
Bundled files	1
License	Apache-2.0
Last updated	October 26, 2026
Links	Skill source ↗ · Repository ↗

Mozgi check

What we found in the skill files. Details come with a subscription.

Security

medium risk · 1 point needs attention

Compatibility

needs extra software

Similar skills

62 similar skills found

Also with subscription

Installation

A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.

Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.

Install the “agent-browser” skill from mozgi.io (https://mozgi.io/skills/vercel-labs-agent-browser/) for me.

1. Download the archive: https://mozgi.io/skills/vercel-labs-agent-browser/download
   If it fails, take the skill folder from the source: https://github.com/vercel-labs/agent-browser/tree/main/skills/agent-browser
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “agent-browser” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/agent-browser/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/vercel-labs/agent-browser.git /tmp/agent-browser
mkdir -p .claude/skills
cp -r /tmp/agent-browser/skills/agent-browser .claude/skills/agent-browser

Restart Claude Code — the skill appears in the list; call it manually with /agent-browser. For all projects use ~/.claude/skills.

git clone --depth 1 --branch main https://github.com/vercel-labs/agent-browser.git /tmp/agent-browser
mkdir -p .agents/skills
cp -r /tmp/agent-browser/skills/agent-browser .agents/skills/agent-browser

Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $agent-browser. For all projects use ~/.agents/skills.

git clone --depth 1 --branch main https://github.com/vercel-labs/agent-browser.git /tmp/agent-browser
mkdir -p .cursor/skills
cp -r /tmp/agent-browser/skills/agent-browser .cursor/skills/agent-browser

Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.

git clone --depth 1 --branch main https://github.com/vercel-labs/agent-browser.git /tmp/agent-browser
mkdir -p .gemini/skills
cp -r /tmp/agent-browser/skills/agent-browser .gemini/skills/agent-browser

Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.

Review the source files

1 file Download Zip

Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.

SKILL.md contents

Original author text · read-only

agent-browser

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs.

Install: npm i -g agent-browser && agent-browser install

Start here

This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the actual workflow content from the CLI:

agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full      # include full command reference and templates

The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skills get core.

Specialized skills

Load a specialized skill when the task falls outside browser web pages:

agent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack             # Slack workspace automation
agent-browser skills get dogfood           # Exploratory testing / QA / bug hunts
agent-browser skills get derive-client     # Record a HAR, derive a standalone API client for a site
agent-browser skills get vercel-sandbox    # agent-browser inside Vercel Sandbox microVMs
agent-browser skills get protected-vercel-deployments  # Access protected Vercel deployments
agent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers

Run agent-browser skills list to see everything available on the installed version.

Why agent-browser

Fast native Rust CLI, not a Node.js wrapper
Works with any AI agent (Cursor, Claude Code, Codex, Continue, Windsurf, etc.)
Chrome/Chromium via CDP with no Playwright or Puppeteer dependency
Accessibility-tree snapshots with element refs for reliable interaction
Sessions, authentication vault, state persistence, video recording
Specialized skills for Electron apps, Slack, exploratory testing, cloud providers

Observability Dashboard

The dashboard runs independently of browser sessions on port 4848 and can also be opened through a proxied or forwarded URL such as https://dashboard.agent-browser.localhost. Agents should stay on the dashboard origin: session tabs, status, and stream traffic are proxied internally, so session ports do not need to be exposed.

Frequently asked questions

What does the agent-browser skill do?

Browser automation CLI for AI agents for navigation, form actions, extraction, screenshots, QA, and app testing.

How do I install agent-browser?

Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.

Which AI models work with agent-browser?

Skills are plain Markdown instructions (the Agent Skills format), so agent-browser works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.

Is agent-browser free?

The skill is published openly by vercel-labs under the Apache-2.0 license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.

Is it safe to install skills?

A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.

How is a skill different from an MCP server or a plugin?

An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.

Related skills

All skills →

agent-browser A command-line tool for browser automation that enables AI agents to interact with websites, fill forms, extract data, take screenshots, and test web applications via the CDP protocol. vercel-labs44.4k

react-best-practices Vercel React best practices for rendering performance, bundle efficiency, and scalable component architecture. vercel-labs33k

to-prd Turns a conversation into a PRD and publishes it to the issue tracker. mattpocock304k

tdd Red-green-refactor workflow for building features and fixes one slice at a time. mattpocock304k

diagnosing-bugs Systematic bug diagnosis through reproduce, minimize, hypothesize, instrument, and fix. mattpocock304k

domain-modeling Builds and sharpens project domain models and terminology. mattpocock304k