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. 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. 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
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.
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.
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.
| Layer | What it does | Neighbors we coexist with |
|---|---|---|
| L3 — Meta-Factory / Team-Architecture Factory (us) | Domain sentence → agent team + skills, via 6 pre-defined team patterns | — |
| L3 — Meta-Factory / Runtime-Configuration Factory | Deterministic, repeatable runtime configurations | coleam00/Archon |
| L3 — Meta-Factory / Codex Runtime Port | Same concept, Codex runtime | SaehwanPark/meta-harness |
| L2 — Cross-Harness Workflow | Standardize skills/rules/hooks across multiple harnesses | affaan-m/ECC |
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.
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
/plugin marketplace add revfactory/harness
/plugin install harness@harness-marketplace
# Copy the skills directory to ~/.claude/skills/harness/
cp -r skills/harness ~/.claude/skills/harness
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
Trigger in Claude Code with prompts like:
Build a harness for this project
Design an agent team for this domain
Set up a harness
| Mode | Description | Recommended For |
|---|---|---|
| Agent Teams (default) | TeamCreate + SendMessage + TaskCreate | 2+ agents requiring collaboration |
| Subagents | Direct Agent tool invocation | One-off tasks, no inter-agent communication needed |
| Pattern | Description |
|---|---|
| Pipeline | Sequential dependent tasks |
| Fan-out/Fan-in | Parallel independent tasks |
| Expert Pool | Context-dependent selective invocation |
| Producer-Reviewer | Generation followed by quality review |
| Supervisor | Central agent with dynamic task distribution |
| Hierarchical Delegation | Top-down recursive delegation |
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/
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.
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.
| Repo | Their position | Relationship to Harness |
|---|---|---|
| coleam00/Archon | "harness builder" — deterministic, repeatable runtime configurations | Same L3, neighbor sub-layer. Archon is a Runtime-Configuration Factory, Harness is a Team-Architecture Factory. Pick Archon for runtime determinism, Harness for team architecture, or combine them. |
| SaehwanPark/meta-harness | Codex port of the same concept | Same L3, different runtime. Use Harness on Claude Code, meta-harness on Codex. |
| affaan-m/ECC | "Agent harness performance & workflow layer" (sits on top of existing harnesses) | Different layer. ECC is a standardization layer across harnesses; Harness is a factory that generates harnesses. Serial combination possible. |
| wshobson/agents | Subagent / skill catalog (182 agents, 149 skills) | Factory ↔ parts supply. wshobson is a catalog to shop from; Harness designs the team. Absorb wshobson entries as parts inside a Harness-generated team. |
| LangGraph | State-graph orchestration, LLM-agnostic | Different track. LangGraph is for long-running, state-recoverable orchestration; Harness is for fast Claude-Code-native team design. |
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.
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.
| Metric | Without Harness | With Harness | Improvement |
|---|---|---|---|
| Average Quality Score | 49.5 | 79.3 | +60% |
| Win Rate | — | — | 100% (15/15) |
| Output Variance | — | — | -32% |
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.
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1A. 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:
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:
A. Currently the official runtime is Claude Code only. A Codex port of the same concept — 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:
Apache 2.0
Attck on Titan Harness Tutorial
Gueivinier R. · 334K views
Chest Harness Tutorial WITHOUT KNOTS
Yisi selfties · 235K views
Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI
AI Engineer · 142K views
“Hi Hacker News, I have become a huge fan in the last several weeks. I am proud to present my first submission. For the last few months I have been working on CleanTab a guitar and bass tablature site that harnesses HTML5…”
“Quantum clues to consciousness: the brain may harness the zero-point field”
“Introducing Omnigent: A Meta-Harness to Combine, Control and Share Your Agents - Databricks — Databricks”
“Revelate Hammerhead Harness Review: Natural Evolution - BIKEPACKING.com — BIKEPACKING.com”
“Xiaomi's new open source, agentic AI coding harness MiMo Code beats Claude Code at ultra-long, 200+ step tasks - Venturebeat — Venturebeat”
AI
Companies use AI to filter candidates. I just gave candidates AI to choose companies. Career-Ops (career-ops.org, also known as careerops) turns any AI coding CLI into a full job search command center. Instead of manually tracking applications in a spreadsheet, you get an AI-powered pipeline that: Career-ops is agentic: Claude Code navigates career pages with Playwright, evaluates fit by reasoning about your CV vs the job description (not keyword matching), and adapts your resume per listing.
AI
CLI-Anything: Bridging the Gap Between AI Agents and the World's Software 🌐 CLI-Hub: pip install cli-anything-hub then cli-hub install — browse, install, and manage all community-built CLIs. Want to add your own? Open a PR — the hub updates instantly. 🎬 See Demos: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts — CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.
AI
A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan. A full, hover-to-play tour lives on the landing page (docs/index.html). Defaults work out of the box: clone, run, then configure models/search/email inside Settings. Only edit .env for deployment-level overrides like APPBIND, APPPORT, AUTHENABLED, DATABASEURL, or a pre-seeded admin password.
AI
Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it. This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time PyTorch shows up, you already know what it's doing under the hood. Each lesson runs the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste deploys,