OpenHarness
Description
SDD 规格驱动开发 + Harness 多 Agent 编排；支持在 OpenCode、Claude Code、Codex CLI 间切换执行引擎，完成从规格到落地的自动化开发任务。
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
openHarness wires spec-driven development (SDD) and a Harness multi-agent loop into one CLI. Swap execution engines (OpenCode, Claude Code, Codex CLI); runtime state lives under .openharness/ in your project.
Write specs first, run the loop second, inspect state throughout.
openHarness is built for real project workflows, not just one-shot code generation.
简体中文 | English
Quick start · How it works · Install · Commands · Layout · Contributing
Quick start
Before the commands, the key mental model is simple: openHarness is a **spec input layer + orchestrated execution loop**, not a single prompt runner.
What you get
- 🧭 Spec entry points: start from
tech-stack.md, PRD, techspec, or change-scopedinput/changes/. - 🛠 Execution loop: `Orchest
Related Skills
Awesome Go
A curated list of awesome Go frameworks, libraries and software
next.js
| The React Framework | 138360 | 1503 | 1 |
sharing-skills
skill for guidance.
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger.
Template Skill
Minimal skeleton for a new skill project structure.
Third-party Notices
THE FOLLOWING SETS FORTH ATTRIBUTION NOTICES FOR THIRD PARTY SOFTWARE THAT MAY BE CONTAINED IN PORTIONS OF THI