A Korean developer released a Claude Code plugin called Harness, which has already garnered 3.6k stars. It solves the era’s most overlooked problem: “I have Claude Code, but I don’t know how to organize it into a team.” Just say “build a harness for this project”, and it automatically generates: a complete agent team definition (.claude/agents/), the skills these agents use (.claude/skills/), and one of six team architecture patterns (Pipeline / Fan-out / Expert Pool / Producer-Reviewer / Supervisor / Hierarchical Delegation). But what surprised me most is that it openly published A/B experiment data: · 15 software engineering tasks · Average quality score: 49.5 → 79.3 (+60%) · Win rate: 15/15 (100%) · Output variance: -32% · The harder the task, the greater the improvement (Basic +23.8 / Advanced +29.6 / Expert +36.2). What surprised me even more is its academic honesty: every time it cites that +60% figure, it faithfully appends “n=15, author-measured, third-party replications pending”. Such restraint is rare in the AI world.

https://github.com/revfactory/harness…

revfactory/harness

Source: https://github.com/revfactory/harness

Harness — The Team-Architecture Factory for Claude Code

English | 한국어 | 日本語

Harness is a team-architecture factory for Claude Code. Say “build a harness for this project” (English) or “하네스 구성해줘” (한국어) or “ハーネスを構成して” (日本語), and the plugin turns your domain description into an agent team and the skills they use — picked from six pre-defined team-architecture patterns.

Overview

Harness leverages Claude Code’s agent team system to decompose complex tasks into coordinated teams of specialized agents. Say “build a harness for this project” and it automatically generates agent definitions (.claude/agents/) and skills (.claude/skills/) tailored to your domain.

Category — Where Harness Sits

Harness lives at the L3 Meta-Factory layer of the Claude Code ecosystem — the layer that generates other harnesses rather than being one. Inside L3, we pick a specific sub-layer: Team-Architecture Factory.

Archon generates deterministic runtime configurations. Harness generates team architectures (pipeline, fan-out/fan-in, expert pool, producer-reviewer, supervisor, hierarchical delegation) plus the skills agents use. Different sub-layers of the same L3. Pick Archon for runtime determinism, Harness for team architecture, or combine them.

Star History

[Star History Chart]

Key Features

• Agent Team Design — 6 architectural patterns: Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, and Hierarchical Delegation
• Skill Generation — Auto-generates skills with Progressive Disclosure for efficient context management
• Orchestration — Inter-agent data passing, error handling, and team coordination protocols
• Validation — Trigger verification, dry-run testing, and with-skill vs without-skill comparison tests

Workflow

Phase 1: Domain Analysis
         ↓
Phase 2: Team Architecture Design (Agent Teams vs Subagents)
         ↓
Phase 3: Agent Definition Generation (.claude/agents/)
         ↓
Phase 4: Skill Generation (.claude/skills/)
         ↓
Phase 5: Integration & Orchestration
         ↓
Phase 6: Validation & Testing

Installation

Via Marketplace

Add the marketplace

/plugin marketplace add revfactory/harness

Install the plugin

/plugin install harness@harness-marketplace

Direct Installation as Global Skill

# Copy the skills directory to ~/.claude/skills/harness/
cp -r skills/harness ~/.claude/skills/harness

Plugin Structure

harness/
├── .claude-plugin/
│   └── plugin.json              # Plugin manifest
├── skills/
│   └── harness/
│       ├── SKILL.md              # Main skill definition (6-Phase workflow)
│       └── references/
│           ├── agent-design-patterns.md   # 6 architectural patterns
│           ├── orchestrator-template.md   # Team/subagent orchestrator templates
│           ├── team-examples.md           # 5 real-world team configurations
│           ├── skill-writing-guide.md     # Skill authoring guide
│           ├── skill-testing-guide.md     # Testing & evaluation methodology
│           └── qa-agent-guide.md         # QA agent integration guide
└── README.md

Usage

Trigger in Claude Code with prompts like:

Build a harness for this project
Design an agent team for this domain
Set up a harness

Execution Modes

Architecture Patterns

Output

Files generated by Harness:

your-project/
├── .claude/
│   ├── agents/                # Agent definition files
│   │   ├── analyst.md
│   │   ├── builder.md
│   │   └── qa.md
│   └── skills/                # Skill files
│       ├── analyze/
│       │   └── SKILL.md
│       └── build/
│           ├── SKILL.md
│           └── references/

Use Cases — Try These Prompts

Copy any prompt below into Claude Code after installing Harness:

Deep Research

Build a harness for deep research. I need an agent team that can investigate any topic from multiple angles — web search, academic sources, community sentiment — then cross-validate findings and produce a comprehensive report.

Website Development

Build a harness for full-stack website development. The team should handle design, frontend (React/Next.js), backend (API), and QA testing in a coordinated pipeline from wireframe to deployment.

Webtoon / Comic Production

Build a harness for webtoon episode production. I need agents for story writing, character design prompts, panel layout planning, and dialogue editing. They should review each other's work for style consistency.

YouTube Content Planning

Build a harness for YouTube content creation. The team should research trending topics, write scripts, optimize titles/tags for SEO, and plan thumbnail concepts — all coordinated by a supervisor agent.

Code Review & Refactoring

Build a harness for comprehensive code review. I want parallel agents checking architecture, security vulnerabilities, performance bottlenecks, and code style — then merging all findings into a single report.

Technical Documentation

Build a harness that generates API documentation from this codebase. Agents should analyze endpoints, write descriptions, generate usage examples, and review for completeness.

Data Pipeline Design

Build a harness for designing data pipelines. I need agents for schema design, ETL logic, data validation rules, and monitoring setup that delegate sub-tasks hierarchically.

Marketing Campaign

Build a harness for marketing campaign creation. The team should research the target market, write ad copy, design visual concepts, and set up A/B test plans with iterative quality review.

Coexistence — Harness and Neighbors

Harness is not alone in the Claude Code / agent-framework ecosystem. The following repos live in adjacent layers; each is described in a parallel “X is …, Harness is …” form so you can pick the one that fits your need or combine several.

Built with Harness

Harness 100

revfactory/harness-100 (https://github.com/revfactory/harness-100) — 100 production-ready agent team harnesses across 10 domains, available in both English and Korean (200 packages total). Each harness ships with 4-5 specialist agents, an orchestrator skill, and domain-specific skills — all generated by this plugin. 1,808 markdown files covering content creation, software development, data/AI, business strategy, education, legal, health, and more.

Research: A/B Testing Harness Effectiveness

revfactory/claude-code-harness (https://github.com/revfactory/claude-code-harness) — A controlled experiment across 15 software engineering tasks measuring the impact of structured pre-configuration on LLM code agent output quality.

Key finding: effectiveness scales with task complexity — the harder the task, the greater the improvement (+23.8 Basic, +29.6 Advanced, +36.2 Expert).

Exact phrasing to use everywhere: +60% avg quality (49.5 → 79.3), 15/15 win-rate, −32% variance (n=15, author-measured A/B, third-party replications pending).

Full paper: Hwang, M. (2026). Harness: Structured Pre-Configuration for Enhancing LLM Code Agent Output Quality.

Requirements

• Agent Teams enabled (https://code.claude.com/docs/en/agent-teams): CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

FAQ

Q1. Isn’t “+60%” oversold? A. The +60% figure comes from an author-measured A/B (n=15, 15 tasks, measured on the sister repo claude-code-harness). Every citation in this repo pairs the number with the disclosure “n=15, author-measured, third-party replications pending” in the same sentence. For adoption decisions, we recommend running a 2–4 week internal pilot and measuring your own numbers. Evidence: - Author A/B: revfactory/claude-code-harness (https://github.com/revfactory/claude-code-harness) - Paper: Hwang, M. (2026). Harness: Structured Pre-Configuration for Enhancing LLM Code Agent Output Quality

Q2. Why “harness factory” and not “harness builder”? Isn’t this competing with Archon? A. Archon generates deterministic runtime configurations — it’s a Runtime-Configuration Factory. Harness generates agent team architectures (team structure, message protocols, review gates) — it’s a Team-Architecture Factory. They are neighbor sub-layers of the same L3 Meta-Factory and serve different needs. Pick Archon for runtime determinism, Harness for team-architecture patterns, or combine them (design architecture with Harness → deploy runtime with Archon). Evidence: - Archon self-definition: clawfit docs/reference-levels.md (https://github.com/hongsw/clawfit/blob/main/docs/reference-levels.md) - Sub-layer declaration: see the Category — Where Harness Sits section above - Archon repo: github.com/coleam00/Archon (https://github.com/coleam00/Archon)

Q3. Isn’t “Claude Code only” too narrow? What about Gemini/Codex? A. Currently the official runtime is Claude Code only. A Codex port of the same concept — SaehwanPark/meta-harness (https://github.com/SaehwanPark/meta-harness) — is already public, so Codex teams can start there. Harness chose “Claude-Code-native, deep” over “multi-runtime, shallow”; cross-runtime collaboration with sibling repos (meta-harness, harness-init, OpenRig) is on the roadmap. Evidence: - Codex port: github.com/SaehwanPark/meta-harness (https://github.com/SaehwanPark/meta-harness) - Cross-runtime scaffolder: github.com/Gizele1/harness-init (https://github.com/Gizele1/harness-init)

License

Apache 2.0