Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
By moondongmin
Agent team builder: dynamic project analysis, custom agents/skills, and dual-leader pipelines (tdd-leader + team-leader)
Build a backend-focused agent team (framework/architecture/ORM detection + Project_Context injection)
Build a frontend-focused agent team (framework/rendering/a11y/perf detection + Project_Context injection)
Build agent team and skills for the project
Show available oh-my-harness skills and usage
Run full team implementation workflow (analyze β plan β implement β review β security β verify)
π Strategic Architecture & Debugging Advisor β code analysis, root cause diagnosis, evidence-based architectural guidance that adapts to the detected project style (READ-ONLY)
π Severity-rated code review β logic defects, SOLID checks, security, performance, spec compliance (READ-ONLY)
π Root-cause analysis, regression isolation, build/compilation error resolution β minimal fix specialist
β‘ Focused task executor for implementation β writes code to pass tests, smallest viable diff
π‘ OWASP Top 10 vulnerability detection, secrets scanning, dependency audit (READ-ONLY)
Backend-only harness builder. Scans the project root to detect language / framework / architecture_style / data_layer / api_style / test_stack, then generates the core 6 agents + 2 leaders + conditional specialists with concrete project evidence injected. Triggers: 'λ°±μλ νλ€μ€ λ§λ€μ΄μ€', 'harness-be', 'backend harness', team setup on server projects (NestJS / Express / Fastify / FastAPI / Django / Spring / Go etc.), reconfiguring an existing harness from a backend perspective, and automatic invocation when the router skill (harness) branches to BE.
Frontend-only harness builder. Scans React / Vue / Angular / Svelte projects to detect framework / meta_framework / rendering_model / state / styling / test_stack / has_storybook / has_i18n, then generates the core 6 + 2 leaders + the 4 mandatory frontend agents (ui-reviewer / a11y-auditor / perf-auditor / component-test-engineer) + conditional specialists. Triggers: 'νλ‘ νΈμλ νλ€μ€ λ§λ€μ΄μ€', 'harness-fe', 'frontend harness', team setup on frontend projects (Next.js / Nuxt / SvelteKit / Remix / Vite SPA etc.), reconfiguring an existing harness from a frontend perspective, and automatic invocation when the router skill (harness) branches to FE.
Router that auto-detects project type and delegates to the backend or frontend harness. Actual agent team construction is performed by harness-be (backend) or harness-fe (frontend). Triggers: 'νλ€μ€ λ§λ€μ΄μ€', 'νλ€μ€ ꡬμ±ν΄μ€', 'νλ€μ€ ꡬμΆν΄μ€', 'νλ€μ€ μ€κ³', 'νλ€μ€ μμ§λμ΄λ§', 'μμ΄μ νΈ ν ꡬμ±ν΄μ€', 'ν μΈν ν΄μ€', 'harness λ§λ€μ΄μ€', 'build harness', 'oh-my-harness', and β when a project already has a harness β 'ꡬνν΄μ€', 'κ°λ°ν΄μ€', 'μμ μμ'.
General-purpose implementation orchestrator powered by an agent team. The team-leader coordinates an architectβexecutorβcode-reviewerβsecurity-reviewerβdebugger team to perform large-scale construction/refactoring/structural changes/migrations. Triggers: 'νμΌλ‘ ꡬνν΄μ€', 'μμ΄μ νΈ νμΌλ‘ μμ ', '리ν©ν λ§ν΄μ€', 'ꡬ쑰 λ³κ²½ν΄μ€', 'ꡬ쑰 κ°μ ', 'λκ·λͺ¨ λ³κ²½', 'μν€ν μ² λ³κ²½', 'λκ·λͺ¨ 리ν©ν λ§', 'λ§μ΄κ·Έλ μ΄μ ν΄μ€', 'λͺ¨λ μΆκ°', 'μ κΈ°λ₯ μ€κ³+ꡬν', 'ν μν¬', 'team work', 'νμΌλ‘ κ°λ°'. Use aggressively when the project has a harness in place and the user requests a sizable change.
Agent team orchestrator that implements features via TDD (Test-Driven Development). The tdd-leader coordinates an architectβtest-engineerβexecutorβcode-reviewerβsecurity-reviewerβdebugger team to drive Red-Green-Refactor cycles automatically. Triggers: 'TDDλ‘ κ΅¬νν΄μ€', 'tdd', 'ν μ€νΈ λ¨Όμ μμ±νκ³ κ΅¬νν΄μ€', 'ν μ€νΈ μ£Όλλ‘ κ°λ°ν΄μ€', 'Red-Green-Refactor', 'λ λ κ·Έλ¦° 리ν©ν°', 'κΈ°λ₯ ꡬνν΄μ€', 'μ΄κ±° λ§λ€μ΄μ€', 'tddλ‘ μμ ', 'TDD μν¬νλ‘μ°', 'test-first', 'ν μ€νΈ νΌμ€νΈ'. Use aggressively when the project has a harness in place and the user requests new feature implementation.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
A Claude Code plugin that analyzes your project and auto-builds a tailored agent team
πΊπΈ English γ» π°π· νκ΅μ΄
Originally, a harness is the set of straps, reins, and gear you put on a horse β the tack that lets a rider hold a powerful animal in place and steer it toward useful work. The word crossed into engineering as a metaphor: a test harness is the wiring of inputs, stubs, and assertions that lets a unit run in isolation. The same idea spread to evaluation harnesses for ML models (e.g. lm-evaluation-harness), and in the LLM era it reappeared as the agent harness β the prompts, tools, and guardrails that hold an LLM in place while it does real work.
oh-my-harness takes that last meaning one step further. Instead of dropping in a generic agent scaffold, it scans your project first, detects the stack and architecture, and then builds a scaffold tailored to the evidence it found β a team of specialized agents where each one only carries the context it actually needs. The horse is still the LLM; the harness is now cut to the shape of your project.
Say "harness", get a team.
Scans your project to detect framework, architecture, and test stack, then injects that evidence directly into agent prompts to build a project-tailored agent team. No DDD/Hex/NestJS baked in β those lenses only activate when the actual code says so.
Claude Code is powerful, but one agent doing design, implementation, testing, review, security, and debugging all at once leads to bloated context and inconsistent quality.
oh-my-harness fixes this:
domain-expert only when Hexagonal is detected).claude/, survives across sessions<Project_Context> block (new in v1.0.0)1. Install the plugin
/plugin marketplace add MoonDongmin/oh-my-harness
/plugin install oh-my-harness
2. Codex CLI (optional, recommended)
npm install -g @openai/codex
codex login
Without Codex CLI, coding agents fall back to Claude Sonnet.
3. Build a harness in your project
/oh-my-harness:harness
Auto-detects project type and delegates to harness-be (backend) or harness-fe (frontend). You can also invoke them directly:
/oh-my-harness:harness-be # backend-only
/oh-my-harness:harness-fe # frontend-only
| Command | Description |
|---|---|
/oh-my-harness:harness | Router β auto-detects BE/FE and delegates |
/oh-my-harness:harness-be | Backend harness builder (framework/architecture/ORM detection) |
/oh-my-harness:harness-fe | Frontend harness builder (framework/rendering/a11y/perf detection) |
/oh-my-harness:tdd | TDD team pipeline (Red β Green β Refactor, category-aware) |
/oh-my-harness:implement | General team implementation (refactoring, migration, structural change) |
/oh-my-harness:verify | Verify changes (build, tests, typecheck) |
/oh-my-harness:help | Help |
Each agent has distinct permissions and specialization. Their base prompts are framework-neutral; the harness injects actual project evidence via a <Project_Context> block at generation time.
Strategic advisor. Analyzes architecture and diagnoses root causes. READ-ONLY β never touches code, only reads and recommends with file:line evidence.
npx claudepluginhub moondongmin/oh-my-harness --plugin oh-my-harnessOrchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
wshobsonMakes a repo agent-ready: AGENTS.md, boundary tests, CI pipeline, GC scripts β based on OpenAI's harness engineering methodology
Gizele111 agents, 35 skills, 18 commands, 9 hooks β spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
komlukThe team-architecture factory for Claude Code β a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Codeμ© ν μν€ν μ² ν©ν 리: λλ©μΈ ν λ¬Έμ₯μ μμ΄μ νΈ νκ³Ό μ€ν¬ μΈνΈλ‘ λ³ννλ λ©ν μ€ν¬.
revfactoryPortable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.
first-flukeMulti-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
jessepwj