agent-browser

Automate browser navigation, form filling, and data extraction via Bash commands.

Updated Jan 14, 2026
One-click install
npx skills add https://github.com/Brite-Nites/brite-claude-plugins --skill agent-browser-brite-nites
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Brite-Nites/brite-claude-plugins/tree/main/plugins/workflows/skills/agent-browser
Command: npx skills add https://github.com/Brite-Nites/brite-claude-plugins --skill agent-browser-brite-nites

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for web testing, form filling, and data extraction, reducing manual effort and error-prone steps.

Core Features & Use Cases

  • Automate navigation and element interaction via refs derived from page snapshots
  • Capture screenshots and extract data across websites for QA, demos, and documentation
  • Provide a repeatable, Bash-based command surface to script deterministic browser automation

Quick Start

Open a URL with agent-browser open, snapshot interactive elements with agent-browser snapshot -i, then perform actions using refs.

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 interactions for web testing without manual clicking?

Automate browser interactions by using a Bash-based command surface to navigate websites, click elements, and fill forms deterministically. It simulates user behavior across websites to reduce manual testing effort and errors.

How do I capture screenshots and extract data across websites for QA?

Capture screenshots and extract data by navigating to a URL and using page snapshots. The toolset captures visual states and extracts information for repeatable QA processes, demos, and documentation generation.

How does form filling and element clicking work with page snapshots?

Element clicking and form filling use interactive element refs derived from page snapshots. You take a snapshot of interactive elements, then perform actions like filling or clicking by referencing those specific snapshot refs.

Can I script deterministic browser automation using a Bash CLI?

Yes, you can script deterministic browser automation using a Bash-based command surface. It provides a repeatable command structure to open URLs, snapshot elements, and perform scripted navigation and data capture.

What are the limitations of using snapshot refs for browser automation?

Using snapshot refs for browser automation requires taking a snapshot before interacting with elements. If the page structure changes dynamically between snapshots, previously captured refs may become invalid, requiring a new snapshot to proceed.