agent-browser

Automate headless browser interactions via CLI for scraping, testing, and form filling.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/cgasgarth/opencode-config --skill agent-browser-cgasgarth
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/cgasgarth/opencode-config/tree/main/skill/agent-browser
Command: npx skills add https://github.com/cgasgarth/opencode-config --skill agent-browser-cgasgarth

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a command-line interface for headless browser automation, enabling AI agents to interact with web pages programmatically for tasks like scraping, testing, and form filling.

Core Features & Use Cases

  • Web Scraping: Extract data from websites.
  • Automated Testing: Simulate user interactions for web application testing.
  • Form Filling: Programmatically fill out web forms.
  • Headless Operations: Perform browser tasks without a visible UI.
  • Use Case: An AI agent needs to check the availability of a product on an e-commerce site. It can use agent-browser to open the product page, extract the stock information, and report back.

Quick Start

Use the agent-browser skill to open the website example.com and take a screenshot named page.png.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping with a headless browser for an AI agent?

To automate web scraping with a headless browser, this Skill provides a CLI that enables AI agents to programmatically open pages and extract data without a visible UI. It supports session management and AI-assisted element selection.

Can I simulate user interactions for automated testing without a visible browser UI?

Yes, you can simulate user interactions for automated testing without a visible UI using headless browser operations. The Skill allows AI agents to programmatically interact with web pages to test web applications.

How do AI agents locate web elements for form filling programmatically?

AI agents locate web elements for form filling using semantic locators and accessibility tree snapshots. This allows the CLI to identify and interact with specific targets on a web page to programmatically fill out forms.

Do I need npm to run headless browser automation tasks?

Yes, you need npm to run headless browser automation tasks because the Skill requires the npm package `agent-browser` for execution. This package provides the necessary CLI environment for AI agents to operate.

What is the best way to manage browser sessions when automating web interactions?

The best way to manage browser sessions when automating web interactions is through the Skill's built-in session management. This maintains state across multiple CLI commands for continuous headless browser operations.

Can I use this approach to check product availability on e-commerce sites?

Yes, you can use this approach to check product availability on e-commerce sites. An AI agent can open a product page, extract stock information using headless browser automation, and report the results.