sd0xdev/sd0x-dev-flow

185 stars · Last commit 2026-08-02

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.

PluginWorkflow & Automation TDD & Testing Debugging Documentation Design & UI DevOps & Infra Productivity AI & Prompting Data & ML Security

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.

**Let the model choose the path. Keep "done" verifiable.**

v4 gives Claude discretion inside a closed, test-pinned anchor set; hooks preserve gate receipts across compaction, and Codex reviews independently.

Full control plane on Claude Code. Skills-only distribution for Codex CLI and other compatible agents.

<!-- BEGIN:HERO-COUNT -->
98 bundled · 98 public 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)

View full repository on GitHub →