Agent Browser

Automate headless browser navigation, interaction, and data extraction via structured commands.

3|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/0xharryriddle/codex-field-kit --skill agent-browser-0xharryriddle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/0xharryriddle/codex-field-kit/tree/main/archive/upstream/examples/codex-skills/skills/agent-browser
Command: npx skills add https://github.com/0xharryriddle/codex-field-kit --skill agent-browser-0xharryriddle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Core Features & Use Cases

  • Navigation: open, back, forward, reload
  • Interaction and extraction: click, fill, get text, get html, get url, snapshot
  • Multi-session orchestration: run isolated browser instances for parallel tasks

Quick Start

Open a URL with agent-browser, perform a few interactions, and capture a snapshot to verify results.

Frequently Asked Questions about Agent Browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate headless browser tasks with AI agents?

You can automate headless browser tasks with AI agents by sending structured commands like open, click, fill, and snapshot. This Rust-based CLI executes navigation, interaction, and data extraction operations with a Node.js fallback for reliability.

What is the best way to extract text and HTML from web pages in automation pipelines?

The best way to extract text and HTML in automation pipelines is using structured CLI commands like get text, get html, and get url. These commands enable AI agents to capture page content during headless browser sessions.

Can I run isolated browser instances for parallel web testing?

Yes, you can run isolated browser instances for parallel web testing using multi-session orchestration. This allows AI agents to execute concurrent navigation, interaction, and data extraction tasks across independent browser sessions.

Does this headless browser automation tool require a Rust environment?

The tool uses a fast Rust-based core but includes a Node.js fallback, meaning it does not strictly require a Rust environment. This dual implementation ensures AI agents can execute browser commands across different setups.

What commands are available for navigating and interacting with modern web interfaces?

Available commands for navigating and interacting with modern web interfaces include open, back, forward, reload, click, fill, get text, get html, get url, and snapshot. These cover navigation, interaction, data extraction, and testing workflows.

Why use a Rust-based core with a Node.js fallback for web automation?

A Rust-based core with a Node.js fallback provides high performance for headless browser automation while maintaining compatibility. This ensures AI agents can execute navigation and interaction commands reliably across different environments.