# web-browser

Hands your agent a real Chrome: page navigation, clicks, form filling, screenshots, console and network inspection. Useful when a live browser beats scraping HTML.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 677 installs · ★ 3195
- Author: mitsuhiko
- License: LicenseRef-Stolen-from-Mario · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mitsuhiko/agent-stuff/tree/HEAD/skills/web-browser/SKILL.md
- Updated: 2026-09-27
- HTML: https://affpapa.org/en/nevibecode/skills/web-browser

## What it does

The skill ships a set of scripts that talk to Chrome or Chromium over the Chrome DevTools Protocol. Launch with `./scripts/start.js --headless`, then `nav.js` opens a URL, `eval.js` runs JavaScript in the active tab, and `screenshot.js` captures the viewport or the whole document. Mobile presets such as `iphone-14` and `pixel-7` come from `emulate.js`; `dismiss-cookies.js` clears consent banners and `pick.js` lets you select elements by clicking.

Everything runs against a separate profile under `~/.cache/agent-web/browser/`, so your everyday Chrome stays untouched. Headless launches disable extensions — a copied profile still carries cookies and browser state, but extension-based features are gone. If `:9222` is already taken by something unknown, startup fails instead of reusing it. Point `BROWSER_DEBUG_PORT` at another port or `BROWSER_BIN` at a non-standard Chrome binary when needed.

Background logging of console output, errors and network traffic starts with the browser and lands as JSONL; `logs-tail.js` dumps or follows it, `net-summary.js` groups the responses. `pick.js` needs a visible window, so start without `--headless`. Switching between headless and headed means stopping the skill browser first with `stop.js`, otherwise it will not relaunch with the new settings.

## Requirements
- Works with: Chrome

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mitsuhiko/agent-stuff web-browser
```

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

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/mitsuhiko/agent-stuff --path skills/web-browser
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mitsuhiko/agent-stuff --skill web-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/mitsuhiko/agent-stuff/tree/HEAD/skills/web-browser/SKILL.md

## When to use it
- capture a screenshot of a page for a report
- fill in a form and verify the submission
- catch a console error right after a click
- see which requests the frontend fires
- check layout in a mobile viewport

## Example prompts
- Open `https://example.com` in headless Chrome and take a full-page screenshot
- Run `document.querySelectorAll("a").length` in the active tab
- Emulate `iphone-14`, reload the page and show me the network log

## 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

From the same set: [mitsuhiko/agent-stuff](https://affpapa.org/en/nevibecode/by/mitsuhiko/agent-stuff.md) — 5 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