Claude Code Plugin

Build Agent Teams
That Actually Work

Harness is a meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use — all from a single prompt.

0
Quality Improvement
0
Win Rate (15/15 tasks)
0
Generated Files in Harness 100
0
Architecture Patterns

Everything You Need to
Orchestrate Agent Teams

From domain analysis to validation, Harness automates the entire lifecycle of building multi-agent systems.

Agent Team Design

6 battle-tested patterns — Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, and Hierarchical Delegation.

Skill Generation

Auto-generates skills with Progressive Disclosure, keeping context lean and loading details only when needed.

Orchestration

Message-based, task-based, and file-based data passing between agents with built-in error handling and fallback strategies.

Validation

Trigger verification, dry-run testing, and with-skill vs without-skill A/B comparison tests to prove quality gains.

Try These Prompts

Copy any prompt into Claude Code after installing Harness. Click to expand.

🔎

Deep Research

Multi-agent investigation teams

Fan-out/Fan-in
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.Click to copy
🌐

Website Development

Full-stack build pipeline

Pipeline
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.Click to copy
🎨

Webtoon Production

Creative team for episodic content

Producer-Reviewer
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.Click to copy
🎥

YouTube Content

End-to-end video planning

Supervisor
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.Click to copy
🔍

Code Review

Parallel multi-dimension audit

Fan-out/Fan-in
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.Click to copy
📚

Technical Docs

Docs from codebase analysis

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

Data Pipelines

End-to-end data workflows

Hierarchical Delegation
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.Click to copy
🚀

Marketing Campaign

Campaign asset creation & testing

Producer-Reviewer
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.Click to copy

6-Phase Workflow

Say “build a harness” and Harness runs a structured 6-phase pipeline to produce production-ready agent teams.

01

Domain Analysis

Analyze your codebase, identify task types, detect user expertise, and prevent conflicts with existing agents.

02

Team Architecture Design

Choose between Agent Teams and Subagents, select from 6 architectural patterns, and define agent separation criteria.

03

Agent Definition Generation

Generate .claude/agents/*.md files with roles, principles, I/O protocols, and team communication contracts.

04

Skill Generation

Create skills with YAML frontmatter, pushy trigger descriptions, and Progressive Disclosure (metadata → body → references).

05

Integration & Orchestration

Wire agents together with orchestrator skills, data-passing protocols, error handling, and team size guidelines.

06

Validation & Testing

Structure checks, trigger verification, dry-run tests, with/without-skill comparison, and iterative refinement.

6 Architecture Patterns

Pick the right coordination strategy for your workload. Click a pattern to learn more.

Pipeline

Sequential dependent tasks

Fan-out / Fan-in

Parallel independent tasks

Expert Pool

Context-dependent selection

Producer-Reviewer

Generate then verify

Supervisor

Central dynamic dispatch

Hierarchical Delegation

Top-down recursive split

Pipeline

Each agent's output feeds directly into the next. Ideal for workflows where steps are strictly ordered — code generation → review → testing → deployment. Simple to reason about, but the chain is only as fast as the slowest link.

Proven by Research

A controlled A/B experiment across 15 software engineering tasks at 3 difficulty levels.

Basic
55.4
79.2
Advanced
49.0
78.6
Expert
44.0
80.2
Without Harness With Harness
+60%
Average quality improvement

100% win rate across all 15 test cases

32% less variance — more consistent, predictable output

Scales with complexity — the harder the task, the bigger the gain

Read the Paper →

100 Ready-Made Harnesses

Production-ready agent teams across 10 domains. 200 packages (EN + KO). 1,808 files. All generated by this plugin.

Content Creation
Software Dev
Data & AI/ML
Business Strategy
Education
Legal & Compliance
Health & Lifestyle
Communication
Operations
Specialized Domains
Explore Harness 100 →

Get Started in Seconds

Two commands. That’s it.

1Add the marketplace
> /plugin marketplace add revfactory/harness
2Install the plugin
> /plugin install harness@harness

Then just say: “Build a harness for this project”