agent-browser

Automate browser interactions for navigation, form filling, and data extraction.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/Chris-Maskey/opencode-config --skill agent-browser-chris-maskey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Chris-Maskey/opencode-config/tree/main/skills/agent-browser
Command: npx skills add https://github.com/Chris-Maskey/opencode-config --skill agent-browser-chris-maskey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

agent-browser removes the repetitive, manual work of interacting with web pages by providing a CLI-first browser automation workflow that can navigate sites, fill forms, click elements, capture screenshots, extract content, and run tests reliably.

Core Features & Use Cases

  • Interactive, compact snapshots that produce short refs for elements so agents can act with minimal context and token usage.
  • Full workflow support for navigation, form filling, authentication vaults, session save/load, downloads, annotated screenshots, visual diffs, and performance profiling.
  • Flexible environment support including headed/headless modes, mobile simulators, proxy configuration, CDP connection, and session isolation for concurrent scrapers or E2E tests.
  • Use Case: Automate logging into a protected dashboard, extract structured data, save the authenticated state for reuse, and perform visual regression comparisons between staging and production.

Quick Start

Open https://example.com, take an interactive snapshot to identify element refs, fill the login form, and save the authenticated session state to auth.json.

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 scraping behind a login form?

You can automate web scraping behind a login by navigating to the page, taking interactive snapshots to identify form element refs, filling the login credentials, and saving the authenticated session state to a file for reuse.

Can I run end-to-end testing and visual regression on mobile simulators?

Yes, you can run end-to-end testing and visual regression on mobile simulators. The workflow supports mobile simulator environments, headed and headless modes, and annotated screenshots to perform visual diffs between staging and production.

What is an interactive compact snapshot in browser automation?

An interactive compact snapshot in browser automation produces short refs for web page elements so agents can act with minimal context and token usage. This mechanism allows efficient navigation, clicking, and form filling without processing the entire page DOM.

Does this browser automation workflow support concurrent sessions and proxies?

Yes, this browser automation workflow supports concurrent sessions and proxies. It provides session isolation for concurrent scrapers or E2E tests, alongside proxy configuration and CDP connection support for managing multiple isolated browser environments.

How do I extract structured page data from a website?

To extract structured page data from a website, navigate to the target URL and use the automation workflow to capture interactive snapshots and pull content directly from the elements. This supports authenticated scraping and multi-session data extraction workflows.

What's the best way to manage downloads during automated web interactions?

The best way to manage downloads during automated web interactions is using a CLI-first browser automation workflow that includes built-in download management. This handles file retrieval programmatically alongside navigation, form filling, and session state management.