Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/amondnet/yoonmoon/proofreadnpx skills add amondnet/yoonmoon --skill proofreadgit clone --depth 1 https://github.com/amondnet/yoonmoonWhat 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 | $0.00283 | $0.01667 |
| Opus 5 | $0.00142 | $0.00834 |
| Sonnet 5 | $0.00057 | $0.00333 |
| Haiku 4.5 | $0.00028 | $0.00167 |
Grade A, and why
proofread 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 3d 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
교정·교열(proofread) — 한국어 어문 규범 교정
윤문(humanize·translate-polish)이 더 좋게 다듬는 도구라면, 이 스킬은 틀린 것을 맞게 고치는 도구다. 규범으로 분류되지 않는 어색함은 손대지 않는다(그건 윤문의 일이다).
references/proofreading-rules.md— 맞춤법·띄어쓰기·표준어·외래어·문장부호·비문 6대 분류와 자주 틀리는 항목·교정 원칙. Phase 1~2에서 읽는다.
- 뜻·문체·격식 불변: 어투·높임 수준·강조·문장 구조는 그대로. 오직 규범 오류만 교정.
- 과교정 금지: 규정상 허용되는 복수 표기(원칙/허용)는 틀린 게 아니다. 일관성만 통일한다.
- 불확실하면 표시: 사이시옷·두음·띄어쓰기 허용처럼 판단이 갈리면 고치지 말고 '확인 요망'으로 표시.
-
한 줄 상태 —
완료. 교정 N건 (맞 a · 띄 b · 표 c · 외 d · 부 e · 문 f) / 확인 요망 M건 -
교정본 — 마크다운 코드블록 또는 인용으로 전체 제시.
-
교정 내역 표
# 분류 원문 → 교정 근거 1 맞 됬다 → 됐다 '되어'='돼' (한글 맞춤법) 2 띄 할수있다 → 할 수 있다 의존명사 '수' 띄어쓰기 … … … … -
(있으면) 확인 요망 — 판단이 갈려 고치지 않고 표시만 한 항목(사용자 선택 요청).
What ships with it
1 file 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.
- 3d ago First seen · 93 lines · 283 tokens per session scan A 3b27db676c2d
proofread is a skill published in the GitHub repository amondnet/yoonmoon (12 stars, last pushed 12d ago), licensed MIT. It adds 283 tokens to every session and 1,667 once invoked, about $0.0014 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.
Other skills, from other repositories
seedance-vocab-ko
This skill should be used when the user asks for Korean Seedance 2.0 prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Korean.
privacy-global-jp
한국+일본 병기 처리방침·이용약관 자동 생성. 한국 본사가 일본 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·일본어(APPI) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.
privacy-global
한국+EU 병기 처리방침·이용약관 자동 생성. 한국 본사가 EU 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·영문(GDPR) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.
humanize-korean
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI…
korean-report-style
Korean-language conventions for technical reports, progress updates, meeting agendas, software handoffs, architecture documents, runbooks, API references, model evaluations, and consortium deliverables — prose register, framing of shortfalls and risks, terminology accuracy, and structural integrity after edits. Use…
create-kr-patch
Use for Korean (Hangul) fan translations of retro console or PC games, including ROM or disc analysis, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction and reinsertion, code hooks, patch builds, and emulator verification. Apply it to both new investigations and follow-up work in…