agentmods.dev

harness

harness is a skill for Claude Code from IISweetHeartII/oh-my-harness. It costs 257 tokens per session (11,105 once invoked), scanned A, original, Apache-2.0.

A setup and maintenance skill for an agent harness—a project structure that defines specialized agents and reusable skills.

In plain words
What is it for?
Use it to create, extend, audit, synchronize, or update agent teams and their skills for a project.
Why use it?
It helps turn an informal automation idea into defined roles and instructions, while checking existing project and user-wide configurations for conflicts.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the oh-my-harness plugin — 2 skills, 3 commands, 1 hook shipped together

not rated 1repo 14d ago A scan 257 tokens original Apache-2.0

Good fit Use it to create, extend, audit, synchronize, or update agent teams and their skills for a project.

Compare 6 skills from other repositories ↓
View source ↗ IISweetHeartII/oh-my-harness
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add IISweetHeartII/oh-my-harness
Claude Code
/plugin install oh-my-harness

Made for: Claude Code.

Or install oh-my-harness, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/iisweetheartii/oh-my-harness/harness/github.svg)](https://agentmods.dev/skills/iisweetheartii/oh-my-harness/harness)
Your own site
<a href="https://agentmods.dev/skills/iisweetheartii/oh-my-harness/harness"><img src="https://agentmods.dev/badge/skills/iisweetheartii/oh-my-harness/harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/iisweetheartii/oh-my-harness/harness"><img src="https://agentmods.dev/badge/skills/iisweetheartii/oh-my-harness/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 257 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00257 $0.11105
Opus 5 $0.00129 $0.05553
Sonnet 5 $0.00051 $0.02221
Haiku 4.5 $0.00026 $0.01111

Measured 11d ago against content hash f08db4e9e725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/harness/SKILL.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness v2 — Agent Team & Skill Architect

도메인/프로젝트에 맞는 하네스를 구성하고, 각 에이전트의 역할을 정의하며, 에이전트가 사용할 스킬을 생성하는 메타 스킬.

핵심 원칙:

  1. 에이전트 정의(.claude/agents/)와 스킬(.claude/skills/)을 생성한다. 에이전트는 "누가", 스킬은 "어떻게"를 담는다.
  2. 실행 모드는 작업의 제어 흐름 형태로 결정한다. — 결정적 제어 흐름은 워크플로우 오케스트레이션, 반복 협상·장기 협업은 퍼시스턴트 에이전트, 단발 위임은 서브에이전트. (Phase 2 참조)
  3. 모델은 업무 특성으로 선택한다. — 업무의 복잡도·작업 기간·자율성·응답 속도에 따라 opus(설계·코드 생성·복잡한 분석·교차 검증, 계획·장기 자율 실행) / sonnet(로그 파싱·포맷 변환·단순 수집 등 일상·기계적 업무)을 에이전트별로 선택한다. (Phase 3 모델 정책 참조)
  4. CLAUDE.md에 하네스 포인터를 등록한다. — 새 세션에서 오케스트레이터 스킬이 트리거되도록 최소한의 포인터(트리거 규칙 + 변경 이력)만 기록한다.
  5. 하네스는 고정물이 아니라 진화하는 시스템이다. — 매 실행 후 피드백을 반영하고, 에이전트·스킬·CLAUDE.md를 지속 갱신한다. 회고와 델타 포착은 harness:evolve 스킬이 담당한다.

워크플로우

Phase 0: 현황 감사

하네스 스킬이 트리거되면 가장 먼저 기존 하네스 현황을 확인한다.

  1. 프로젝트/.claude/agents/, 프로젝트/.claude/skills/, 프로젝트/CLAUDE.md를 읽는다 1-1. 유저 스코프도 함께 읽는다 — ~/.claude/agents/, ~/.claude/skills/. 프로젝트 스코프가 유저 스코프를 덮어쓰기 때문에, 프로젝트에 같은 이름을 만들면 사용자가 이미 쓰던 전역 에이전트가 조용히 사라진다. 에러가 나지 않으므로 발견이 늦다.

  2. 현황에 따라 실행 모드를 분기한다:

    • 신규 구축: 에이전트/스킬 디렉토리가 없거나 비어있음 → Phase 1부터 전체 실행
    • 기존 확장: 기존 하네스가 있고 새 에이전트/스킬 추가 요청 → 아래 Phase 선택 매트릭스에 따라 필요한 Phase만 실행
    • 운영/유지보수: 기존 하네스의 감사·수정·동기화 요청 → Phase 7 운영/유지보수 워크플로우로 이동

    기존 확장 시 Phase 선택 매트릭스:

    변경 유형 Phase 1 Phase 2 Phase 3 Phase 4 Phase 5 Phase 6
    에이전트 추가 건너뜀 (Phase 0 결과 활용) 배치 결정만 필수 (3-0 포함) 전용 스킬 필요 시 (4-0 포함) 오케스트레이터 수정 필수
    스킬 추가/수정 건너뜀 건너뜀 건너뜀 필수 (4-0 포함) 연결 변경 시 필수
    아키텍처/모드 변경 건너뜀 필수 영향받는 에이전트만 (3-0 포함) 영향받는 스킬만 (4-0 포함) 필수 필수

  3. v1 하네스 감지: 기존 오케스트레이터에 TeamCreate/TeamDelete/CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS 참조가 있으면 v1 산출물이다. 현행 런타임에서 깨지므로 마이그레이션을 제안한다 (references/execution-modes.md의 "v1 → v2 마이그레이션" 참조).

  4. 기존 에이전트/스킬 목록과 CLAUDE.md 기록을 대조하여 불일치(drift)를 감지한다

  5. 감사 결과를 사용자에게 요약 보고하고, 실행 계획을 확인받는다

Read the full file on GitHub · 469 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 469 lines · 257 tokens per session scan A f08db4e9e725

Subscribe to this mod's changes

harness is a skill published in the GitHub repository IISweetHeartII/oh-my-harness (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 257 tokens to every session and 11,105 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude Codeagent-teamai-agentsclaude-code-pluginharnessmeta-skill
Related

Other skills, from other repositories

harness-zh

A simplified-Chinese meta-skill for designing and maintaining a harness, meaning a coordinated system of agents and skills for a project or field. It audits the current setup, defines agent roles, creates skills, and keeps the setup synchronized.

nilecui/harness-zh-release · 203 tokens

harness

A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.

revfactory/harness · 170 tokens

ship

A final delivery check for a project or product release. It verifies that planned features are complete, the build and tests pass, and a validation sample reaches the required result.

andrewcigan/vibe-dev-plugin · 59 tokens

stuck

A procedure for handling a coding task that is stuck after repeated failed attempts or a long period without progress. It stops the repeated approach, reviews possible causes, and proposes different paths forward.

andrewcigan/vibe-dev-plugin · 68 tokens

choose-stack

A guided process for choosing one software technology stack based on an application's main architectural bottleneck.

andrewcigan/vibe-dev-plugin · 82 tokens

dev-plan

A planning tool that breaks a software project into features arranged in dependency-based waves, or groups of work that can be done in sequence or parallel.

andrewcigan/vibe-dev-plugin · 77 tokens