agent-browser

Files (1)

• SKILL.md

SKILL.md (first lines)

# Browser Automation with agent-browser

> **Version:** 0.29.1 (Rust-based CLI with Node.js fallback)

## Installation

### npm (recommended)

```bash
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps
```

### Homebrew

```bash
brew install agent-browser
```

### Cargo

```bash
cargo install agent-browser
```

### From Source

```bash
git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install
```

### Maintenance

```bash
agent-browser upgrade       # Upgrade to the latest version
agent-browser doctor        # Diagnose install issues
agent-browser doctor --fix  # Auto-clean stale files
agent-browser profiles      # List available Chrome profiles
```

## Quick start

```bash
agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser
```

## Core workflow

1. Navigate: `agent-browser open <url>`
2. Snapshot: `agent-browser snapshot -i` (returns elements with refs like `@e1`, `@e2`)
3. Interact using refs from the snapshot
4. Re-snapshot after navigation or significant DOM changes

---

## Commands

### Navigation

```bash
agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close [--all]   # Close browser (--all closes every session)
```

### SPA / Client-side Navigation

For single-page applications (Next.js, React Router, etc.) where `open` would trigger a full page reload:

```bash
agent-browser pushstate <url>   # SPA client-side navigation
```

`pushstate` auto-detects `window.next.router.push` (triggers RSC fetch on Next.js) and falls back to `history.pushState` + `popstate`/`navigate` events for other frameworks.

### Snapshot (page analysis)

```bash
agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (recommended)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector
```

**Snapshot options:**

| Flag | Description |
|---|---|
| `-i, --interactive` | Only interactive elements |
| `-c, --compact` | Remove empty structural elements |
| `-d, --depth <n>` | Limit tree depth |
| `-s, --selector <sel>` | Scope to CSS selector |

### Interactions (use @refs from snapshot)

```bash
agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down (e.g. before click for modifiers)
agent-browser keyup Shift         # Release held key
agent-browser keyboard type <text>    # Type with real keystrokes (no selector)
agent-browser keyboard inserttext <text>  # Insert text without key events

From nordeim/neo-crm, MIT.