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/skill-authoring/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/skill-authoring)<a href="https://agentmods.dev/skills/cookyman74/my_harness/skill-authoring"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/skill-authoring/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/skill-authoring"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/skill-authoring.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 3 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 | $0.00180 | $0.00758 |
| Opus 5 | $0.00090 | $0.00379 |
| Sonnet 5 | $0.00036 | $0.00152 |
| Haiku 4.5 | $0.00018 | $0.00076 |
Grade A, and why
skill-authoring 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 10d 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.
What it actually says
skill-authoring — 하네스 스킬 본문 유지보수
skills/harness/의 SKILL.md + 6개 references 정합성을 지키며 개선한다.
왜
이 레포는 스킬 문서 자체가 제품이다. Phase 번호·매트릭스·체크리스트·reference 포인터가 서로 얽혀 있어 한 곳만 고치면 다른 곳이 거짓이 된다. 단일 출처 원칙으로 중복을 막는다.
트리거
- 사용: "스킬 본문 수정", "하네스 스킬 개선", "Phase 추가/수정", "reference 정리", "체크리스트 업데이트", "스킬 문서 다시 손봐줘" 등 기존
skills/harness/본문·reference 유지보수 요청. - 트리거 금지(near-miss, 유사하나 대상 아님):
- 새 스킬을 처음부터 생성 → my-harness 팩토리.
- README·릴리스 노트만 수정 → doc-syncer / release-manager.
- 에이전트 정의(
*.md) 자체 수정 → 해당 에이전트 담당.
절차
- 영향 범위 파악 — 수정 대상이 SKILL.md인지 reference인지, 다른 파일의 포인터/번호에 영향 주는지 확인.
- 단일 출처 적용 — 규칙은 한 곳에만. SKILL.md=포인터+요약, reference=상세. 중복 발견 시 reference로 이동하고 포인터만 남김.
- 크기 관리 — SKILL.md ≤500줄. 초과 시 분리. 300줄+ reference엔 상단 ToC.
- 연쇄 갱신 — Phase 추가/삭제 시 Phase 선택 매트릭스 + 산출물 체크리스트 + 관련 reference 동시 갱신.
- 하향 영향 알림 — 본문 변경이 README 설명과 어긋나면
doc-syncer에, 버전 영향 있으면release-manager에 알림. - 검증 —
repo-qa에 포인터 무결성 + Phase 번호 일관성 검증 요청.
작성 원칙 (본문에도 적용)
- "Why를 설명" — 강압 지시보다 이유.
- 명령형, lean하게, 일반화(오버피팅 금지).
- 반복 코드는
scripts/번들.
후속 실행
변경 요약은 _workspace/{phase}_skill-maintainer_changes.md. "다시 손봐줘"는 직전 변경 요약을 읽고 이어서.
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.
- 10d ago First seen · 35 lines · 180 tokens per session scan A ae969b4cc036
skill-authoring is a skill published in the GitHub repository cookyman74/my_harness (80 stars, last pushed today), licensed Apache-2.0. It adds 180 tokens to every session and 758 once invoked, about $0.0009 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…