Harness Loom banner
KingGyuSuh KingGyuSuh

Harness Loom

Development community

Description

Install and grow a reviewed-work harness in any repository. Ships three user-invocable skills for Claude Code, Codex CLI, and Gemini CLI.

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

[!IMPORTANT] **This repository is archived.** `harness-loom` was built for the era when coding assistant CLIs shipped neither a native harness nor `/goal`. That gap no longer exists: the native harness (dynamic workflows, sol/terra ultra) and `/goal` (an evolution of the Ralph loop) are now built into the assistants themselves. Out of respect for each vendor's native harness — Codex and Claude alike — this project is archived. The code remains available read-only for reference; there will be no further releases.

harness-loom logo

harness-loom

[English](README.md) | [한국어](docs/README.ko.md) | [日本語](docs/README.ja.md) | [简体中文](docs/README.zh-CN.md) | [Español](docs/README.es.md)

[![Version](https://img.shields.io/badge/version-0.3.5-blue.svg)](./CHANGELOG.md) [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](./LICENSE) [![Platforms](https://img.shields.io/badge/platforms-Claude%20Code%20%7C%20Codex%20%7C%20Gemini-purple.svg)](#multi-platform)

**Tune a production-specific harness on top of the generic harness shipped by modern coding assistants.**


What It Does

`harness-loom` is a factory plugin that installs a runtime harness into a target repository and grows it pair by pair. The factory ships four user-facing slash commands (`/harness-init`, `/harness-auto-setup`, `/harness-pair-dev`, `/harness-goal-interview`) plus a `sync.ts` script. Once installed, your target gets a planner, an orchestrator, a shared control plane under `.harness/`, and a place to add project-specific producer-reviewer pairs over time.

This is harness fine-tuning, not model fine-tuning — you encode your repo's review standards, task shapes, and definition of done into versioned infrastructure instead of re-prompting it every session. `harness-loom` is for teams that already see production-quality potential in their