agent-browser

Automate browser interactions with element refs and snapshot commands.

Updated Aug 23, 2026

Search Tags:#automation #testing #cli #scripting #browser #web #data-extraction

Ready to run

npx skills add https://github.com/CjLogic/nanocrew --skill agent-browser-cjlogic

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/CjLogic/nanocrew/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/CjLogic/nanocrew --skill agent-browser-cjlogic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate web browsing to research topics, interact with web apps, fill forms, take screenshots, and extract data, reducing manual overhead and speeding up web-based tasks.

Core Features & Use Cases

Automated Navigation: Open URLs and browse pages to gather information.
Element Interaction & Data Extraction: Click, fill, and read data from dynamic web pages.
Stateful Automation & Reporting: Take snapshots, save results, and maintain session context for repeatable tasks.

Quick Start

Open a URL and begin automating browser interactions using the agent-browser commands.

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 research and browser interactions via CLI?▼

Automate web research and browser interactions by using a sandboxed CLI environment to open pages, click elements, fill forms, and extract data. This approach reduces manual overhead and accelerates web-based tasks through stateful automation.

Can I extract data from dynamic web pages using scripting?▼

Yes, you can extract data from dynamic web pages using scripting. The automation environment maintains session context and allows you to take snapshots, click elements, and read data across websites for repeatable data extraction tasks.

What is a sandboxed browser environment for automation?▼

A sandboxed browser environment for automation is an isolated execution space that enables stateful actions like opening URLs and filling forms. It applies a defined CLI surface with element references and snapshot commands to ensure safe, repeatable web interactions.

Does automated web browsing support form filling and stateful sessions?▼

Yes, automated web browsing supports form filling and stateful sessions. The environment maintains session context across pages, allowing you to execute sequential actions like logging in, clicking elements, and taking snapshots for reporting.

What are the limitations of using a CLI for browser automation?▼

A limitation of using a CLI for browser automation is that interactions rely on element references and snapshot commands rather than visual rendering. This requires precise element targeting and may require adjustments when web page structures change.