my_harness: Skill for Claude Code

.claude/skills/my-harness/SKILL.md

my-harness is a skill for Claude Code from cookyman74/my_harness. It costs 152 tokens per session (3,281 once invoked), scanned A, original, Apache-2.0.

A factory for creating teams of specialized coding agents and their reusable skills, with a Korean-first workflow. A harness here means the files and rules that organize how those agents work together.

In plain words
What is it for?
Use it to design, build, extend, or inspect an agent team for a project, including its agent files, skills, testing guidance, and review gates.
Why use it?
Building a multi-agent workflow from scratch requires repeating team structure, testing rules, and review practices. This provides patterns and shared rules for creating and improving that setup.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Codex.

This is cookyman74/my_harness's own configuration. It tells Claude Code how to work on my_harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my_harness configures →

Part of the myharness plugin — 7 skills, 6 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to cookyman74/my_harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/skills/my-harness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cookyman74/my_harness

Made for: Claude Code.

Or install myharness, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

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 my-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/cookyman74/my_harness/my-harness/github.svg)](https://agentmods.dev/skills/cookyman74/my_harness/my-harness)
Your own site
<a href="https://agentmods.dev/skills/cookyman74/my_harness/my-harness"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/my-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 my-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/cookyman74/my_harness/my-harness"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/my-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,281 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 8
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00152 $0.03281
Opus 5 $0.00076 $0.01640
Sonnet 5 $0.00030 $0.00656
Haiku 4.5 $0.00015 $0.00328

Measured 11d ago against content hash f6f13eda871b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

my-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.

.claude/skills/my-harness/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

My Harness — 한국어 우선 슬림 팩토리

업스트림 skills/harness/SKILL.md의 핵심 워크플로우를 보존하되, (1) 한국어 우선, (2) 패턴 3종으로 슬림화, (3) 이 레포 전용 기본값을 프리베이크한 개인 포크.

핵심 원칙:

  1. 에이전트 정의(.claude/agents/) + 스킬(.claude/skills/)을 파일로 생성한다.
  2. 에이전트 팀이 기본 실행 모드. 2명 이상 협업이면 팀 먼저 검토.
  3. CLAUDE.md엔 포인터(트리거 규칙) + 변경 이력만 등록.
  4. 하네스는 진화한다 — 실행 후 피드백 반영, 지속 갱신.
  5. 모든 Agent 호출에 model: "opus" 명시.
  6. 품질 게이트 2층. 코드/설계 도메인이면 내부 생성-검증(같은 세션 QA) 외부 리뷰 루프(codex/gemini 독립 검증)를 병행한다. 같은 컨텍스트 QA는 같은 맹점을 공유하므로 외부 독립 관점이 추가 결함을 잡는다.
  7. 생성물에 교리 주입. 생성하는 빌더/수정/QA 에이전트의 작업 원칙에 개발 규칙·TDD 교리를 포인터로 주입(복붙 금지, DRY). 서브에이전트는 글로벌 컨텍스트를 못 받으므로 명시 주입 필요.

깊은 디테일이 필요하면 업스트림/로컬 참조를 읽는다 (중복 작성 금지):

  • 패턴/분리기준/재사용: skills/harness/references/agent-design-patterns.md
  • 스킬 작성: skills/harness/references/skill-writing-guide.md
  • 오케스트레이터: skills/harness/references/orchestrator-template.md
  • QA: skills/harness/references/qa-agent-guide.md
  • 테스트: skills/harness/references/skill-testing-guide.md
  • 실제 예시: skills/harness/references/team-examples.md
  • 개발 규칙(주입용): references/dev-rules.md ([[dev-rules]])
  • TDD 교리(주입용): references/tdd-doctrine.md ([[tdd-doctrine]])
  • 외부 리뷰 게이트: external-review-loop 스킬 (단계 산출물마다 codex/gemini 독립 검증)

패턴 3종 (슬림)

패턴 언제 데이터 흐름
파이프라인 순차 의존 작업 (A 산출물 → B 입력) 단방향 체인
팬아웃/팬인 병렬 독립 수집 후 통합 분산 → 수집
생성-검증 (Producer-Reviewer) 생성 후 품질 검수 필수 생성 → 내부 QA 교차검증 (+ 코드/설계면 외부 리뷰 루프 병행)

감독자/전문가풀/계층위임이 정말 필요하면 업스트림 agent-design-patterns.md로 확장. 기본은 위 3종. 생성-검증을 코드/설계 도메인에 쓸 땐 내부 QA 뒤에 external-review-loop(codex/gemini)를 단계 게이트로 붙인다.

워크플로우 (압축)

Phase 0: 현황 감사

.claude/agents/, .claude/skills/, CLAUDE.md 읽기 → 신규/확장/유지보수 분기. drift(파일 vs CLAUDE.md 이력 불일치) 감지 후 사용자에게 요약 보고.

Phase 1: 도메인 분석

요청에서 도메인·핵심 작업유형(생성/검증/편집/분석) 식별 → 코드베이스 탐색(기술스택·데이터모델·주요모듈) → 기존 에이전트/스킬 충돌·중복 점검 → 사용자 숙련도 감지 후 톤 조절. 직전 단계 결과서(_workspace/)의 ## 다음 단계 참조 블록이 있으면 먼저 읽는다(F5 연속성).

Read the full file on GitHub · 121 lines

Files

What ships with it

2 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 · 121 lines · 152 tokens per session scan A f6f13eda871b

Subscribe to this mod's changes

my-harness is a skill published in the GitHub repository cookyman74/my_harness (80 stars, last pushed today), licensed Apache-2.0. It adds 152 tokens to every session and 3,281 once invoked, about $0.0008 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens