agent-browser

Automate browser navigation, form interaction, screenshots, and data scraping via CDP.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/apollostreetcompany/codex-compound --skill agent-browser-apollostreetcompany
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/apollostreetcompany/codex-compound/tree/main/plugins/compound-engineering/skills/agent-browser
Command: npx skills add https://github.com/apollostreetcompany/codex-compound --skill agent-browser-apollostreetcompany

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive solution for automating browser tasks, from navigating websites and filling out forms to taking screenshots and scraping data.

Core Features & Use Cases

  • Browser Automation: Execute a wide range of browser actions, including navigation, form interaction, and more.
  • Interactive Workflow: Utilize snapshot references for precise element selection and action execution.
  • Use Case: If you need to automate a repetitive task like filling out a web form or testing a web application, this Skill can streamline the process.

Quick Start

Use the agent-browser skill to navigate to 'https://example.com' and click the 'Submit' button.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser tasks like web form filling and navigation?

You can automate browser tasks by using a command-line interface to control Chrome or Chromium actions via the Chrome DevTools Protocol (CDP). This approach streamlines repetitive browser automation workflows like navigation and form interaction without manual input.

Can I use this for web application testing and data scraping?

Yes, this approach is designed specifically for web application testing and data scraping scenarios. It automates browser actions through a command-line interface, allowing you to capture screenshots and extract data from web applications via CDP.

Do I need a specific browser environment to enable remote debugging for web automation?

Yes, web automation requires a configured Chrome or Chromium browser environment with remote debugging enabled. This CDP connection is necessary to execute command-line interface instructions and control the targeted browser actions.

What is the best way to select interactive web elements during browser automation?

The best way to select elements during browser automation is by utilizing snapshot references for precise element targeting. This ensures accurate execution of actions like form filling and button clicks through the command-line interface.

Are there limitations when taking screenshots and scraping data from dynamic web pages?

Limitations include the strict requirement for a configured Chrome or Chromium environment with remote debugging enabled. Without a proper CDP connection, the command-line interface cannot execute browser actions, take screenshots, or scrape data.

Does agent-browser work with Chrome and Chromium for screenshot capture?

Yes, agent-browser works with Chrome and Chromium to perform screenshot capture and other browser automation tasks. It controls the browser environment via the Chrome DevTools Protocol (CDP) using a command-line interface.