Skip to main content
skill CX Codex

agent-browser · actionbook — Claude Code skill: what it does, how to install

This skill lets an agent operate a browser through commands for navigation, form entry, and page checks. Use it for browser tasks inside a coding workflow.

Apache-2.0 136 installs ★ 1,632 updated 2026-10-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add actionbook/actionbook --skill agent-browser -a claude-code
Open on GitHub

What agent-browser does

agent-browser gives an agent a command set for browser control. It can open a URL, return an interactive snapshot with refs such as @e1, click elements, clear and fill fields, type text, press keys, scroll, wait for page state, and read text, the title, or the current URL. After navigation or a major DOM change, the agent should take another snapshot.

The included workflow covers a website indexing request: open the request page, inspect its form, enter the site URL, email, and use case, submit it, wait for network idle, and inspect the result. The browser session should end with agent-browser close. Claude Code needs Bash(agent-browser *) in .claude/settings.local.json, or you can run ./setup.sh to configure that permission.

What it helps with

  • open a page and inspect its controls
  • fill a web form from its interactive refs
  • submit entered data with a button click
  • verify a form submission after loading
  • read the current page title or URL

Example prompts for the agent

  • Open <url>, inspect the interactive elements, and fill the required form fields.
  • Use agent-browser to submit the form, wait for the page to load, and check the result.
  • Find the relevant button on the page, click it, then close the browser session.

How to install agent-browser

1Skills CLI (Vercel)

npx skills add actionbook/actionbook --skill agent-browser -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-browser/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-browser/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agent-browser

How do I install agent-browser in Claude Code?

Run npx skills add actionbook/actionbook --skill agent-browser -a claude-code, then check ~/.claude/skills/agent-browser/SKILL.md.

What does agent-browser do?

It lets an agent navigate pages, inspect interactive elements, fill fields, click controls, wait for page state, and read page information through browser commands.

What permission does agent-browser need in Claude Code?

Add Bash(agent-browser *) to the allow list in .claude/settings.local.json, or run ./setup.sh to configure it.

Source text

SKILL.md · Apache-2.0
---
name: agent-browser
description: Automates browser interactions for form filling and web page interaction. Used by the request-website command to submit website indexing requests.
---

# Browser Automation with agent-browser

## 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
5. **Always close**: `agent-browser close`

## Commands

### Navigation
```bash
agent-browser open <url>      # Navigate to URL
agent-browser close           # Close browser (ALWAYS do this)
```

### Snapshot (page analysis)
```bash
agent-browser snapshot        # Full accessibility tree
agent-browser snapshot -i     # Interactive elements only (recommended)
```

### Interactions (use @refs from snapshot)
```bash
agent-browser click @e1           # Click
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser scroll down 500     # Scroll page
```

### Get information
```bash
agent-browser get text @e1        # Get element text
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
```

### Wait
```bash
agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --load networkidle      # Wait for network idle
```

## Example: Form submission (request-website)

```bash
# Open Actionbook request page
agent-browser open "https://actionbook.app/request-website"

# Get form elements
agent-browser snapshot -i
# Output shows: textbox "Site URL" [ref=e1], textbox "Email" [ref=e2], textbox "Use Case" [ref=e3], button "Submit" [ref=e4]

# Fill form
agent-browser fill @e1 "https://example.com/products"
agent-browser fill @e2 "[email protected]"
agent-browser fill @e3 "Scraping product catalog"

# Submit
agent-browser click @e4
agent-browser wait --load networkidle

# Verify submission
agent-browser snapshot -i

# Close browser
agent-browser close
```

## Permission Required

Add to `.claude/settings.local.json`:
```json
{
  "permissions": {
    "allow": [
      "Bash(agent-browser *)"
    ]
  }
}
```

Or run `./setup.sh` to configure automatically.

© actionbook · Apache-2.0 · actionbook/actionbook

Similar skills

All skills for Browser and scraping →

agent-browser by other authors comes first.

agent-browser vercel-labs This Claude Code skill automates browser interaction for tasks like navigating sites, filling forms, and testing web apps. It also supports exploratory QA and Electron app automation. CX Codex +1 1,600,000installs agent-browser nanocoai A skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode. It hands your agent a real browser: open pages, read articles, fill forms, grab screenshots, pull data, test web UIs. CX Codex +1 ★ 31,137repo stars agent-browser eyadsibai This skill gives an AI agent CLI control over a browser for form entry, page scraping, screenshots, and PDF output. Use it for browser automation tasks. CX Codex +1 166installs agent-browser fcakyon This skill guides an agent through website tasks with agent-browser, from locating page controls to filling forms and capturing screenshots. Use it to gather web data or test a web app. CX Codex +1 ★ 1,216repo stars anti-detect-browser antibrow anti-detect-browser is a Claude Code skill that launches Chromium with a genuine device fingerprint through Playwright API. Each profile persists across runs for testing, scraping, and multi-account work. CX Codex +1 168,800installs browser-mcp-agent antibrow Gives an agent a real browser through MCP calls: navigate, click, fill forms, screenshot, run JS. A named profile keeps the session logged in between runs. CX Codex +1 138,200installs browser-fingerprint-audit liarjsdev browser-fingerprint-audit audits browser fingerprints for internal contradictions using the liarjs CLI. It spots mismatches between browser JavaScript APIs and edge network data. CX Codex +1 132,900installs browser-act BrowserAct browser-act — a skill that hands your agent a browser CLI: navigate, wait for JavaScript, pull data, fill forms, take screenshots. Useful when plain fetch falls short. CX Codex +1 108,500installs browser-use browser-use browser-use is a Claude Code skill that controls Chrome via CDP. It runs during web automation, dynamic site scraping, form submission, and cloud browser orchestration. CX Codex +1 100,100installs browser-act-skill-forge BrowserAct browser-act-skill-forge explores a website through browser-act and forges a skill package with SKILL.md and Python scripts. Later runs skip the exploration step. CX Codex +1 85,200installs

From the same set9

actionbook The actionbook skill gives an agent current action guides for websites, covering navigation, form input, clicks, screenshots, and parallel tab work. CX Codex +1 3,400installs active-research active-research runs a research pass over a topic, arXiv paper or URL and assembles an HTML report. Useful when you want the reading done, not just a list of links. CX Codex +1 3,200installs extract Extracts structured data from websites, outputs JSON or CSV, and writes a standalone Playwright script. CX Codex +1 2,700installs deep-research deep-research conducts in-depth research across arXiv papers and web sources, generating formatted HTML reports with Actionbook automation. CX Codex +1 149installs arxiv-viewer arxiv-viewer is a Claude Code skill for research workflows that searches, downloads, and reads academic papers from arXiv using its official API and ar5iv HTML pages. CX Codex +1 133installs actionbook-scraper The actionbook-scraper skill generates and validates web scraper scripts using verified selectors from Actionbook's database. It auto-validates generated scripts and fixes errors. CX Codex +1 132installs rust-learner rust-learner fetches live Rust updates and crate changelogs from lib.rs or crates.io. Useful when updating Cargo.toml dependencies. CX Codex +1 110installs Actionbook Actionbook drives web pages through your logged-in Chrome browser. Helps AI agents gather structured data and automate web tasks using active user sessions. CX Codex +1 ★ 1,632repo stars

Project sponsors

Companies that keep this analytics open