Development

harness-engineering

by Roy Yuen
New v1.0.0
$8 one-time
License key required after purchase

About this skill

The Harness Engineering skill implements a structured methodology for agent orchestration. It allows you to build sophisticated control loops using a multi-role architecture: Planner: Defines contracts and stop rules. Executor: Performs bounded actions. Verifier: Validates results against evidence. Critic/Recovery: Identifies regressions and manages error state.

Getting started

New to AgentPowers? Learn how to install and use skills - no coding experience required.

How It Works

Step-by-step guide to installing and using skills. Chat-based or terminal - your choice.
Documentation

Full CLI reference, MCP plugin setup, and API docs for developers.

Reviews (0)

More Development Skills

Development

Technical Debt Prevention System - Full

Skill · by Ryan Heltemes

AI writes code fast — and accumulates debt faster. This skill puts enforcement between your AI and every edit. Pre-edit hook blocks files over 1,500 lines. Complexity scoring catches dangerous files that line count misses. A pattern registry stops copy-paste at three strikes. Session baseline flags sudden growth before it compounds. Snapshot command ranks your worst files by priority, on demand.

New $25
Development

Technical Debt Prevention System - Lite

Skill · by Ryan Heltemes

Stop creating debt before it starts. Three checks before every edit: responsibility, size, complexity. One rule for patterns: register it or stop writing it. One rule for events: wire the unsubscribe when you wire the subscribe. No setup. No tooling. Just the discipline that keeps codebases clean.

New $10
Development

prompt-engineer-pro

Skill · by Roy Yuen

Prompt Engineer Pro is a production-grade system for teams shipping AI workflows into business-critical environments. Unlike basic prompting assistants, this skill treats prompts as software assets that require governance, audit trails, and regression testing. It helps you build, audit, and harden prompt stacks for complex tasks involving multiple models, tool-use agents, and structured data extraction.

New $8