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.
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/skills/my-harness/SKILL.mdgit clone --depth 1 https://github.com/cookyman74/my_harnessWrote 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.
[](https://agentmods.dev/skills/cookyman74/my_harness/my-harness)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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:
- 에이전트 정의(
.claude/agents/) + 스킬(.claude/skills/)을 파일로 생성한다. - 에이전트 팀이 기본 실행 모드. 2명 이상 협업이면 팀 먼저 검토.
- CLAUDE.md엔 포인터(트리거 규칙) + 변경 이력만 등록.
- 하네스는 진화한다 — 실행 후 피드백 반영, 지속 갱신.
- 모든 Agent 호출에
model: "opus"명시. - 품질 게이트 2층. 코드/설계 도메인이면 내부 생성-검증(같은 세션 QA) 과 외부 리뷰 루프(codex/gemini 독립 검증)를 병행한다. 같은 컨텍스트 QA는 같은 맹점을 공유하므로 외부 독립 관점이 추가 결함을 잡는다.
- 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-loop스킬 (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 뒤에external-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).
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.
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.
- 11d ago First seen · 121 lines · 152 tokens per session scan A f6f13eda871b
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…