jrenaldi79/harness-engineering

README preview

<div align="center">

# Harness Engineering and Best Practices for Coding Agents

**A reference guide and Claude Code plugin for long-running AI coding agent harnesses**

[![License: MIT](https://img.shields.io/badge/license-MIT-blue?labelColor=1A1C29)](./LICENSE)
[![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen?labelColor=1A1C29)](https://nodejs.org)
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?labelColor=1A1C29)](https://github.com/jrenaldi79/harness-engineering)
[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey?labelColor=1A1C29)](https://github.com/jrenaldi79/harness-engineering)
[![GitHub last commit](https://img.shields.io/github/last-commit/jrenaldi79/harness-engineering?labelColor=1A1C29)](https://github.com/jrenaldi79/harness-engineering/commits)
[![GitHub stars](https://img.shields.io/github/stars/jrenaldi79/harness-engineering?style=social)](https://github.com/jrenaldi79/harness-engineering)

</div>

[Andrej Karpathy](https://x.com/karpathy/status/2035173492447224237) put it bluntly: "The agents do not listen to my instructions." They bloat abstractions, copy-paste code blocks, and ignore style guidance, no matter how carefully you write your AGENTS.md. If the person who coined "[context engineering](https://x.com/karpathy/status/1937902205765607626)" can't get agents to follow written rules, the answer isn't better prompting. It's mechanical enforcement: git hooks that block bad code before it lands, linters that catch what instructions can't, and rule files that load only when relevant so the agent's finite attention isn't wasted.

Harness engineering is context engineering applied to coding agents: structuring rule files, planning before building, enforcing quality with automation, and keeping documentation in sync with code so the agent stays aligned across long sessions.

This repo contains:

View full repository on GitHub →