agent-browser

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

7|1|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/DonaldMurillo/momentum-cms --skill agent-browser-donaldmurillo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/DonaldMurillo/momentum-cms/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/DonaldMurillo/momentum-cms --skill agent-browser-donaldmurillo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often need reliable, scalable web interactions. This skill provides a browser automation CLI that enables navigation, form filling, element interaction, data extraction, and visual capture to automate everyday web tasks.

Core Features & Use Cases

  • Deterministic Actions: open URLs, snapshot page structure, fill fields, click controls, wait for page loads, and capture screenshots or PDFs.
  • Refs-Based Interactions: use compact element refs (@e1, @e2, etc.) to interact with dynamic pages reliably across navigations.
  • Ready-to-Use Templates & References: includes templates for login flows, form automation, and content capture, plus reference docs for advanced usage.
  • Use Case: automate logging into a SaaS dashboard, scrape key metrics, and generate a concise report.

Quick Start

Start by opening a site, snapshotting to discover refs, then fill forms and submit, finally capture results. Example:

  • agent-browser open https://example.com
  • agent-browser snapshot -i
  • agent-browser fill @e1 "[email protected]"
  • agent-browser fill @e2 "password123"
  • agent-browser click @e3
  • agent-browser wait --load networkidle
  • agent-browser screenshot /tmp/dashboard.png

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 tasks like form filling and clicking for AI agents?

You can automate web tasks using deterministic CLI commands for navigation, form filling, and clicking. This approach allows AI agents to interact with modern web apps reliably by executing specific commands to open URLs, fill fields, and click controls.

How does browser automation handle dynamic page elements during navigation?

Browser automation handles dynamic page elements using compact element references, known as refs. By snapshotting the page structure, you get identifiers like @e1 or @e2 to reliably interact with specific controls across navigations.

Can I capture screenshots and extract data from web apps using a CLI?

Yes, you can capture screenshots and extract data from web apps using CLI commands. The automation process supports visual capture by taking screenshots or generating PDFs, and enables data extraction directly from the page content.

What is the best way to automate logging into a SaaS dashboard and scrape metrics?

The best way to automate SaaS dashboard logins and scrape metrics is by using a CLI workflow. You open the URL, snapshot the page to find element refs, fill login fields, click submit, wait for the network to idle, and capture a screenshot.

Do I need to install any dependencies to use this browser automation tool?

No dependencies are required to use this browser automation tool. It provides ready-to-use templates and reference docs for login flows and content capture, allowing you to execute deterministic CLI commands for web interactions without external setup.

Why use deterministic CLI commands for web testing instead of standard scripts?

Deterministic CLI commands ensure scalable and reliable web testing interactions for AI agents. By enforcing a standard command structure for actions like clicking and waiting for page loads, it provides session isolation and consistent execution across modern web apps.