agent-browser

Automate browser interactions for web testing via CLI commands.

3|1|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/jagreehal/jagreehal-claude-skills --skill agent-browser-jagreehal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jagreehal/jagreehal-claude-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/jagreehal/jagreehal-claude-skills --skill agent-browser-jagreehal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates browser interactions for web testing, form filling, and data capture, reducing manual testing time and human error.

Core Features & Use Cases

  • Ref-based workflow for reliable navigation, element interaction, and state capture.
  • Snapshotting elements yields stable refs like @e1, @e2 for repeatable actions.
  • End-to-end browser actions via a CLI: open, click, fill, snapshot, and screenshot, enabling repeatable test scripts.
  • Use Case: Automate a login flow to a dashboard and extract the resulting page title.

Quick Start

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

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 testing and form filling through a CLI?

You can automate web testing and form filling via a CLI using commands like open, snapshot, click, and fill to navigate pages and interact with elements. This approach enables repeatable test scripts for automated login and data extraction workflows.

What is a ref-based workflow for browser automation?

A ref-based workflow for browser automation uses snapshotting to capture interactive elements and assign them stable references like @e1 or @e2. You then use these refs to reliably click or fill inputs, ensuring repeatable actions across multiple pages.

How do I extract data and capture screenshots during web testing?

To extract data and capture screenshots during web testing, navigate to the target page and use the screenshot command to save the state. You can also snapshot interactive elements to extract specific data like page titles or form inputs.

Can I use this browser automation tool for multi-page navigation and login flows?

Yes, this browser automation tool supports multi-page navigation and login flows. You can open a URL, snapshot elements to get refs, fill login inputs, and click buttons to automate navigation across a dashboard and capture the resulting state.

Do I need any specific dependencies to run this browser automation tool?

Yes, you need the agent-browser tool installed to operate this browser automation workflow. It provides the required CLI interface to execute commands like open, snapshot, click, fill, and screenshot for your web testing tasks.