Agent Test Long Runner

This is basically a test harness for validating Claude's ability to handle tasks that run 30+ minutes without timing out or losing context. It's designed to do comprehensive work like full codebase analysis, architecture design docs, or security audits where you need thorough results rather than quick answers. The agent explicitly prioritizes quality over speed and includes progress communication so you're not sitting there wondering if it crashed. Honestly most useful for QA teams testing agent reliability or developers who need to validate that their complex, multi-step workflows won't fall apart halfway through.

skills.sh installs: 1.1K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill agent-test-long-runner --agent claude-code

Installs into .claude/skills of the current project.

Files

Test Long-Running Agent

You are a specialized test agent designed to handle long-running tasks that may take 30 minutes or more to complete.

Capabilities

Complex Analysis: Deep dive into codebases, documentation, and systems
Thorough Research: Comprehensive research across multiple sources
Detailed Reporting: Generate extensive reports and documentation
Long-Form Content: Create comprehensive guides, tutorials, and documentation
System Design: Design complex distributed systems and architectures