harness

Convert feature specs into executable agent tasks with phase management.

Updated Jan 7, 2026
One-click install
npx skills add https://github.com/aimskr/aims-claude-toolkit --skill harness-aimskr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harness
Source: https://github.com/aimskr/aims-claude-toolkit/tree/main/skills/harness
Command: npx skills add https://github.com/aimskr/aims-claude-toolkit --skill harness-aimskr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Coordinating complex feature work across multiple agent roles to ensure every test passes by converting a spec into executable tasks within a structured harness loop.

Core Features & Use Cases

  • Phase-based workflow from spec intake to convergence to orchestrate parallel development.
  • Role-based collaboration (researcher, impl-1..N, tester, reviewer) with clear ownership and progress tracking.
  • Built-in governance: PROGRESS files, mistake logs, and lessons-learned capture for continual improvement.
  • Use cases include scalable teams implementing specs that benefit from parallel execution and test-first validation.

Quick Start

Initialize the harness with your spec and run Phase 1 to generate tests and assemble the agent team.

Frequently Asked Questions about harness

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate test-driven development across multiple agent roles?

Test-driven coordination across agent roles is managed by converting a feature spec into executable tasks within a structured harness loop. This assigns clear ownership to researcher, implementation, tester, and reviewer roles while tracking progress.

Can I use a harness to track progress and log mistakes during feature implementation?

Yes, harness workflows include built-in governance using PROGRESS files, mistake logs, and lessons-learned capture. This ensures safe collaboration rules are satisfied and enables continual improvement throughout the development lifecycle.

Does test-driven harness execution work for multi-module projects requiring scalable teams?

Test-driven harness execution is designed for multi-module projects requiring parallel collaboration. It suits scalable teams implementing complex feature specs that benefit from role-based ownership and phase management.

How do I start a phase-based workflow that converts a feature spec into executable agent tasks?

Initialize the harness with your feature spec and run Phase 1 to generate tests and assemble the agent team. This frontmatter-driven skill unit schema creates an integration-ready artifact structure for subsequent parallel execution.

When should I not use a test-driven parallel development harness?

Avoid using a test-driven parallel development harness for simple, single-module features that lack complex spec requirements. The overhead of phase management, role-based collaboration, and progress tracking is best suited for large-scale parallel execution.