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.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/instructions/cookyman74/my_harness/claude-md)<a href="https://agentmods.dev/instructions/cookyman74/my_harness/claude-md"><img src="https://agentmods.dev/badge/instructions/cookyman74/my_harness/claude-md/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/instructions/cookyman74/my_harness/claude-md"><img src="https://agentmods.dev/badge/instructions/cookyman74/my_harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03034 | $0.03034 |
| Opus 5.5 | $0.01214 | $0.01214 |
| Sonnet 5.5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
my_harness CLAUDE.md 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
이 레포는 harness 플러그인(에이전트 팀 & 스킬 아키텍트 메타 스킬)이다. 세 개의 하네스가 구성되어 있다.
하네스: my-harness (포크판 팩토리)
목표: 도메인 한 문장 → 에이전트 팀 + 스킬을 한국어 우선·슬림(패턴 3종)으로 찍어내는 개인 포크 팩토리.
트리거: 새 도메인/프로젝트용 하네스를 만들거나 확장할 때 my-harness 스킬을 사용하라. 업스트림 디테일이 필요하면 skills/myharness/references/*를 읽는다. 단순 질문은 직접 응답.
하네스: repo-maintainer (이 레포 유지보수)
전제: 프로파일 .claude/skills/repo-maintainer/harness-profile.json (2026-09-22 · 팩토리 1.8.0)
- ⚠ 가정(무응답): 완료 기준 = 테스트 게이트 통과 · CI green · 산출물 경로 존재
- ⚠ 가정(무응답): 비가역 = 릴리스·태그 발행 · 모름 — 비가역으로 취급
- ⚠ 가정(무응답): 실패 비용 = 오류가 더 아프다 — 늦더라도 정확하게
- ⚠ 가정(무응답): 승인 지점 = 「릴리스·태그 발행」 직전 승인 · 「모름 — 비가역으로 취급」 직전 승인 · 중대 단계 승인 사다리(PRD→계획서→실행)
- ⚠ 가정(무응답): 기존 자산 = 재사용 우선 — 에이전트 6·스킬 6
- 비가역: 릴리스·태그 발행 · 모름 — 비가역으로 취급 → 이 목록에 닿는 단계는 중대
목표: 이 레포의 문서 동기화·릴리스·스킬 본문 개선·정합성 검증을 에이전트 팀으로 조율.
트리거: 문서/버전 정합성, 릴리스, 스킬 본문 개선 등 여러 파일·여러 전문성이 얽힌 유지보수 요청 시 repo-maintainer 스킬을 사용하라. 단순 1파일 수정은 직접 처리.
구성: 에이전트 5(doc-syncer, release-manager, skill-maintainer, stabilizer, repo-qa) + 스킬 3(doc-sync, release-flow, skill-authoring) + 오케스트레이터(repo-maintainer). 모드: 에이전트 팀(생성-검증+파이프라인 하이브리드), 전원 model: opus. 안정화 게이트(중대 blast-radius): 팩토리 정본(skills/myharness/) 변경은 skill-maintainer→stabilizer(정책감사 run-policy-audit.sh·외부리뷰 external-review-loop·회귀 드라이런·리스크 등급 조절) 게이트 통과 후 배포. 상세는 각 .claude/agents/*, .claude/skills/*에서 단일 출처로 관리.
알려진 정합성 이슈: 없음. 버전 1.9.0 정합(plugin=marketplace=badge×3=CHANGELOG), bash skills/myharness/scripts/run-policy-audit.sh PASS(fail 0, warn 0). 최신 릴리스 = 1.9.0(2026-09-25 · 모델 배치). ⚠ 공정 코드네임 ≠ 릴리스 버전 — 이 공정의 문서 경로는 docs/v1.8.3/ 이고 릴리스는 1.9.0 이다(직전: 공정 v1.7.6 → 릴리스 1.8.0). 기능 추가라 SemVer minor 로 정했다(릴리스 직전 결정). S0~S6 전 단계 완료(2026-09-24) + 통합 e2e(docs/v1.8.3/todo/00-index.md). HI10(인터뷰 효과 실측)은 보류 상태로 릴리스 — 배선은 검증, before/after 비교는 미실행(docs/v1.7.6/working_history/S5-measurement.md §5).
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.
- 1mo ago Changed · +10 lines · +908 tokens per session c442827e5b24
- 1mo ago Changed · -12 lines · -6,062 tokens per session ab061a6b01dd
- 1mo ago Changed · +2 lines · +843 tokens per session 54dd7ba919a3
- 2mo ago First seen · 55 lines · 7,345 tokens per session scan A aedde3790188
my_harness CLAUDE.md is an instructions file published in the GitHub repository cookyman74/my_harness (88 stars, last pushed 9d ago), licensed Apache-2.0. It adds 3,034 tokens to every session, about $0.0121 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.