Can I use this for testing password-protected sites?

Yes. The skill supports saving and loading browser states, including cookies and local storage, allowing you to maintain authenticated sessions across tasks.

Does it support video recording for debugging?

Yes, it includes built-in commands to start and stop video recordings, which is excellent for verifying automated workflows or debugging failed tests.

How does Claude identify elements on a page?

The skill uses a snapshot command that produces an accessibility tree. This tree assigns unique reference IDs (like @e1) to interactive elements, which Claude uses to target them accurately.

Can I mock API responses with this skill?

Yes, the skill provides network routing capabilities that allow you to intercept requests and return mock JSON or HTML responses.

What is the Agent Browser skill for Claude Code?

It is a specialized plugin that allows Claude to control a web browser, enabling it to navigate websites, interact with UI elements, and extract information for you.

Agent Browser Automation

Name: Agent Browser Automation
Author: outfitter-dev

byoutfitter-dev

Browser Automation

Automates browser-based tasks including web testing, form filling, and data extraction through an interactive CLI.

About

The upstream-agent-browser skill empowers Claude to interact with the web as a functional agent. By providing a comprehensive suite of tools for navigation, element interaction, and state management, it allows Claude to perform complex workflows like end-to-end testing, scraping dynamic content, and automating administrative web tasks. It utilizes a unique referencing system to map interactive elements to simple IDs, ensuring high accuracy when clicking, typing, or extracting data from modern web applications.

Key Features

Comprehensive Interaction Suite: Supports clicking, typing, hovering, scrolling, and drag-and-drop actions.
Interactive Element Mapping: Generates snapshots with reference IDs for precise element targeting.
Parallel Session Management: Run multiple browser instances simultaneously with saved authentication states.
Visual Evidence & Debugging: Capture full-page screenshots, PDFs, and high-quality video recordings of sessions.
0 GitHub stars
Advanced Network & State Control: Intercept network requests, mock API responses, and manage cookies or local storage.

Use Cases

Automated end-to-end testing and visual regression checks for web applications.
Automating repetitive web-based workflows such as form submissions and report generation.
Data extraction and web scraping from JavaScript-heavy or authenticated websites.

About

Key Features

Comprehensive Interaction Suite: Supports clicking, typing, hovering, scrolling, and drag-and-drop actions.
Interactive Element Mapping: Generates snapshots with reference IDs for precise element targeting.
Parallel Session Management: Run multiple browser instances simultaneously with saved authentication states.
Visual Evidence & Debugging: Capture full-page screenshots, PDFs, and high-quality video recordings of sessions.
0 GitHub stars
Advanced Network & State Control: Intercept network requests, mock API responses, and manage cookies or local storage.

Use Cases

Automated end-to-end testing and visual regression checks for web applications.
Automating repetitive web-based workflows such as form submissions and report generation.
Data extraction and web scraping from JavaScript-heavy or authenticated websites.