agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

2|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/0xHoneyJar/rune --skill agent-browser-0xhoneyjar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/0xHoneyJar/rune/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/0xHoneyJar/rune --skill agent-browser-0xhoneyjar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a CLI-driven solution to automate repetitive browser-based tasks, enabling teams to validate UIs, gather data, and verify web workflows without manual clicks.

Core Features & Use Cases

  • Automate navigation, element interaction, form filling, and screenshot capture across web pages.
  • Support Web3 testing workflows with mocked wallets and contract reads via optional integrations.
  • Use cases include end-to-end UI validation, data extraction from dynamic pages, and PR-ready visual documentation.

Quick Start

Open a page: agent-browser open https://example.com Snapshot interactive elements: agent-browser snapshot -i Interact by refs: agent-browser click @e1 Capture a screenshot: agent-browser screenshot Close session: agent-browser close

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 for web testing and form filling?

You can automate browser tasks like web testing and form filling by using a command-line interface to navigate pages, snapshot interactive elements, and interact with them using semantic locators and refs. This streamlines UI validation and data extraction without manual clicks.

Can I use this to automate Web3 testing workflows with mock wallets?

Yes, you can automate Web3 testing workflows by utilizing optional web3-mock integration through Anchor. This allows you to test interactions with mocked wallets and perform contract reads during your automated browser sessions.

How do I capture screenshots for visual documentation during web testing?

To capture screenshots for visual documentation during web testing, you use the screenshot command after navigating to the target page. This enables you to generate PR-ready visual snapshots of dynamic pages automatically.

What is the best way to target and interact with elements on a dynamic page?

The best way to target and interact with elements on a dynamic page is by taking an interactive snapshot to identify elements, then clicking or interacting with them using their specific refs and semantic locators via the command-line interface.

Do I need a command-line interface to automate navigation and data extraction?

Yes, a command-line interface is required to automate navigation and data extraction. It drives the browser interactions, allowing you to open pages, snapshot interactive elements, and close sessions through direct terminal commands.