# agent-browser

This skill hands your agent a browser: open pages, click elements, fill forms, grab screenshots and record video. Useful for scraping and UI testing.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 162800 installs · ★ 12
- Author: 101-skills
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/101-skills/superpowers/tree/HEAD/tools/utilities/agent-browser/SKILL.md
- Updated: 2026-08-31
- HTML: https://affpapa.org/en/nevibecode/skills/101-skills-agent-browser

## What it does

The skill runs on inference.sh and its `belt` CLI. Your agent opens a URL with `belt app run agent-browser --function open` and gets back a list of interactive elements tagged `@e1`, `@e2` and so on. From there it clicks, types, selects, drags or uploads files by referencing those tags. Playwright does the actual work underneath, but the agent never touches selectors.

Those refs go stale fast. Any navigation, form submit or dynamic content load invalidates them, so you have to call `snapshot` again — otherwise the agent keeps clicking numbers that no longer point anywhere. A session persists across calls; `open` returns its id and `close` ends it, handing back the video file if recording was on.

Before anything runs you need the CLI installed and a `belt login` session. The function set covers JavaScript execution on the page, screenshots, proxy routing and video capture with a cursor indicator. Bundled templates handle form filling, authenticated sessions and page capture.

## Requirements
- Works with: Playwright

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill agent-browser -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/agent-browser/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/agent-browser/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill agent-browser -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/agent-browser/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill agent-browser -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/agent-browser/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install 101-skills/superpowers agent-browser
```

2. **Manually: put the files in place**
- File: `.github/skills/agent-browser/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill agent-browser -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/101-skills/superpowers --path tools/utilities/agent-browser
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/agent-browser/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill agent-browser -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/101-skills/superpowers/tree/HEAD/tools/utilities/agent-browser/SKILL.md

## When to use it
- fill out a web form and submit it
- capture a viewport or full-page screenshot
- pull data off a page with custom JavaScript
- record a walkthrough video for debugging
- upload a file into a page input

## Example prompts
- Open https://example.com/login and list the interactive elements
- Fill the Email field with user@example.com and click the sign-in button
- Take a full-page screenshot and record the session as video

## Similar
- [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · 1200000 installs
- [webapp-testing](https://affpapa.org/en/nevibecode/skills/webapp-testing.md) — skill · 186758 installs
- [computer-use](https://affpapa.org/en/nevibecode/skills/computer-use.md) — skill · 239400 installs
- [browser-use](https://affpapa.org/en/nevibecode/skills/browser-use.md) — skill · 98200 installs
- [playwright-cli](https://affpapa.org/en/nevibecode/skills/playwright-cli.md) — skill · 195700 installs
- [last30days](https://affpapa.org/en/nevibecode/skills/last30days.md) — skill · 53000 installs

## Other versions with the same name
- [agent-browser · vercel-labs](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — 1200000 installs
- [agent-browser · nexu-io](https://affpapa.org/en/nevibecode/skills/nexu-io-agent-browser.md) — 2800 installs
- [agent-browser · openai](https://affpapa.org/en/nevibecode/skills/agent-browser.md) — 20 installs

From the same set: [101-skills/superpowers](https://affpapa.org/en/nevibecode/by/101-skills/superpowers.md) — 22 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md