sd0xdev/sd0x-dev-flow

146 stars · Last commit 2026-04-21

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

README preview

# sd0x-dev-flow

![sd0x-dev-flow banner](https://raw.githubusercontent.com/sd0xdev/sd0x-dev-flow/main/banner.jpg)

**Language**: English | [繁體中文](README.zh-TW.md) | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md)

> The harness layer for Claude Code.

**Quality gates that AI can't skip.** A reference implementation of AI Agent Harness Engineering for [Claude Code](https://claude.com/claude-code) — hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts.

<!-- BEGIN:HERO-COUNT -->
95 skills · 15 agents — ~4% of Claude's context window
<!-- END:HERO-COUNT -->

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![npm](https://img.shields.io/badge/npx-skills%20add-blue)](https://www.npmjs.com/package/skills)

## What This Harness Does

> [Harness engineering](https://martinfowler.com/articles/exploring-gen-ai/harness-engineering.html) is the discipline of engineering everything around the LLM — tool loops, context management, hooks, state machines, safety layers — as opposed to training the model itself. Mitchell Hashimoto coined the term in Feb 2026; [Anthropic engineering](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) and [Martin Fowler](https://martinfowler.com/articles/exploring-gen-ai/harness-engineering.html) have published on it; [arXiv 2603.05344](https://arxiv.org/html/2603.05344v1) formalizes it.

View full repository on GitHub →