agent-browser

Automate browser interactions via CLI with snapshots and element refs.

Updated Mar 6, 2026
One-click install
npx skills add https://github.com/mmtftr/bakathon --skill agent-browser-mmtftr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/mmtftr/bakathon/tree/main/.opencode/skills/agent-browser
Command: npx skills add https://github.com/mmtftr/bakathon --skill agent-browser-mmtftr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser-based interactions for AI agents by providing a CLI to control a headless or headed browser, enabling reliable web UI automation within AI workflows.

Core Features & Use Cases

  • Deterministic navigation and interaction: open pages, snapshot the DOM to obtain stable element refs, then perform clicks, fills, and form submissions using those refs.
  • Data extraction and testing: capture page state, take screenshots, and extract text or structured data for validation and documentation.
  • Session management and security: support named sessions, timeouts, and authentication patterns to preserve context across runs and environments.

Quick Start

Open a URL, snapshot the page to obtain refs, then perform actions like fill and click using those refs to automate a simple web form.

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 form filling and clicking with a CLI?

Web form filling via CLI involves opening a URL, snapshotting the DOM to obtain stable element refs, then performing deterministic clicks and fills using those refs. This approach enables reliable browser automation for AI agents without manual intervention.

Can I take screenshots and extract data from web pages during browser automation?

Yes, browser automation CLI supports capturing page state by taking screenshots and extracting text or structured data during navigation. This allows validation and documentation of web app content directly within automated workflows.

How does headless browser automation handle authentication and sessions?

Headless browser automation handles authentication and sessions by supporting named sessions, timeouts, and authentication patterns to preserve context across runs. This ensures secure and continuous interactions across different environments.

What is the best way to reduce context when scripting web automation tasks?

To reduce context in web automation scripting, snapshot the DOM to obtain stable element refs and perform actions using those refs. This deterministic approach minimizes context overhead while maintaining reliable element targeting.

Does CLI browser automation support proxies and safety configurations?

CLI browser automation supports proxies and safety configurations through configurable timeouts and content boundaries. These safety features ensure controlled browser interactions while maintaining session integrity across automated workflows.

Why use deterministic commands for web UI testing instead of manual scripting?

Deterministic commands for web UI testing provide stable element refs from DOM snapshots, ensuring reliable clicks and fills without flaky selectors. This approach reduces test maintenance and enables consistent automation across web apps.