Agent Test Long Runner
Exercise or delegate agent sessions meant to run 30+ minutes on deep analysis, architecture, or long-form documentation without rushing to a shallow answer.
Overview
agent-test-long-runner is an agent skill most often used in Build (also Ship review, Idea research) that configures a long-running test agent for 30+ minute deep analysis, research, and detailed documentation tasks.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-test-long-runnerWhat is this skill?
- Test agent profile designed for complex tasks that may run 30+ minutes
- Emphasizes complex codebase analysis, thorough research, detailed reporting, and system design
- Operating rules: take time, document everything, iterate, and communicate progress
- Structured output: section headers, code examples, text diagrams, citations, and next steps
- Example use cases include refactoring plans, architecture docs, and in-depth research reports
- Designed for tasks that may take 30+ minutes to complete
Adoption & trust: 642 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need to verify or run agents on sprawling tasks where short chat turns produce incomplete analysis and your orchestration may time out too early.
Who is it for?
Agent builders testing extended run behavior or solo founders commissioning exhaustive codebase or architecture analysis in one supervised session.
Skip if: Quick bug fixes, lint-only checks, or production deploy steps where fast deterministic tooling is required.
When should I use this skill?
Invoke with $agent-test-long-runner when you need a specialized test agent for long-running complex analysis, research, reporting, or system design work.
What do I get? / Deliverables
The agent follows long-runner instructions to produce thorough, structured reports with progress updates suitable for refactoring plans, architecture docs, or research deliverables.
- Detailed structured report with headers, examples, references, and next steps
- Progress updates during the long run
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Long-runner behavior is configured while you build and harden agent tooling; the same pattern supports ship-time deep review and operate-scale audits. agent-tooling is the shelf because the skill defines agent behavior and output norms for extended runs, not a single app feature or test suite file.
Where it fits
Validate that your orchestration allows 30+ minute agent sessions without premature termination.
Request a comprehensive codebase analysis and refactoring plan with sections, examples, and action items.
Run thorough multi-source research and an extensive report before committing to a product direction.
Generate long-form tutorials or system design documents with diagrams described in text.
How it compares
Use instead of default fast-reply agent profiles when the goal is depth and documentation length, not minimal patch generation.
Common Questions / FAQ
Who is agent-test-long-runner for?
Developers building or evaluating agent frameworks who need a documented persona for multi-hour analysis, research, and reporting runs.
When should I use agent-test-long-runner?
During Build while tuning agent-tooling and timeout budgets; during Ship review for exhaustive narrative code or architecture review; and during Idea research when compiling in-depth competitive or technical research reports.
Is agent-test-long-runner safe to install?
It is a behavioral test profile that encourages broad reads and long sessions—review the Security Audits panel on this page and cap runtime, cost, and data access in your environment.
SKILL.md
READMESKILL.md - Agent Test Long Runner
--- name: test-long-runner description: Test agent that can run for 30+ minutes on complex tasks category: custom --- # 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 ## Instructions 1. **Take Your Time**: Don't rush - quality over speed 2. **Be Thorough**: Cover all aspects of the task comprehensively 3. **Document Everything**: Provide detailed explanations and reasoning 4. **Iterate**: Continuously improve and refine your work 5. **Communicate Progress**: Keep the user informed of your progress ## Output Format Provide detailed, well-structured responses with: - Clear section headers - Code examples where applicable - Diagrams and visualizations (in text format) - References and citations - Action items and next steps ## Example Use Cases - Comprehensive codebase analysis and refactoring plans - Detailed system architecture design documents - In-depth research reports on complex topics - Complete implementation guides for complex features - Thorough security audits and vulnerability assessments Remember: You have plenty of time to do thorough, high-quality work!