Can I use Agent Browser for authenticated websites?

Yes, the skill includes commands to save and load browser states, allowing you to persist login sessions and cookies across different automation runs.

What is the Agent Browser skill?

Agent Browser is a specialized capability for Claude Code that allows AI agents to control a web browser to perform tasks like navigating pages, clicking buttons, and extracting information.

How does Agent Browser identify elements on a page?

It uses a snapshot command to analyze the page and assign temporary reference IDs (like @e1 or @e2) to interactive elements, ensuring the AI can precisely target the correct items.

Does Agent Browser support visual debugging?

Absolutely. You can take screenshots (standard or full-page) and use the --headed flag to open a visible browser window to watch the automation in real-time.

Is it possible to run multiple browser sessions at once?

Yes, Agent Browser supports named sessions, enabling you to manage multiple independent browser contexts in parallel for complex multi-site workflows.

Agent Browser Automation

Name: Agent Browser Automation
Author: oneqmethod

byoneqmethod

브라우저 자동화

Automates full-featured browser interactions for web testing, data extraction, and form filling directly within the Claude Code environment.

소개

Agent Browser is a powerful skill for Claude Code that enables AI agents to navigate the web, interact with complex DOM elements, and execute automated workflows. It utilizes a robust reference-based system to target elements discovered via snapshots, allowing for reliable clicking, typing, and form submission. With built-in support for authentication state management, parallel sessions, and visual captures, it serves as an essential tool for developers performing end-to-end testing, visual regression, or complex data collection across dynamic web applications.

주요 기능

High-resolution visual capture with full-page and element-specific screenshots
0 GitHub stars
Snapshot-based interactive element targeting using unique @refs
Comprehensive interaction suite including click, fill, hover, and scroll
Support for parallel browser sessions and semantic locator-based searching
Authentication state persistence for managing secure, logged-in sessions

사용 사례

Extracting structured data from dynamic, JavaScript-heavy websites
Automating end-to-end testing and QA workflows for web applications
Automating repetitive web-based administrative tasks and form submissions

소개

주요 기능

High-resolution visual capture with full-page and element-specific screenshots
0 GitHub stars
Snapshot-based interactive element targeting using unique @refs
Comprehensive interaction suite including click, fill, hover, and scroll
Support for parallel browser sessions and semantic locator-based searching
Authentication state persistence for managing secure, logged-in sessions

사용 사례

Extracting structured data from dynamic, JavaScript-heavy websites
Automating end-to-end testing and QA workflows for web applications
Automating repetitive web-based administrative tasks and form submissions