Humanize KR is a command-line coding-agent skill that detects patterns making Korean text look machine-written and rewrites its style, rhythm, and wording while preserving the content. Korean-language writers use it to revise translation-like phrasing, repetitive structures, formulaic expressions, and other listed AI writing patterns. The catalogue includes its agents, skills, instructions, and plugin for supported coding-agent tools.
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 skills add epoko77-ai/im-not-ai --skill commit-kogit clone --depth 1 https://github.com/epoko77-ai/im-not-aiWrote 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/epoko77-ai/im-not-ai/commit-ko)<a href="https://agentmods.dev/skills/epoko77-ai/im-not-ai/commit-ko"><img src="https://agentmods.dev/badge/skills/epoko77-ai/im-not-ai/commit-ko/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/epoko77-ai/im-not-ai/commit-ko"><img src="https://agentmods.dev/badge/skills/epoko77-ai/im-not-ai/commit-ko.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 | $0.00183 | $0.01085 |
| Opus 5.5 | $0.00073 | $0.00434 |
| Sonnet 5.5 | $0.00037 | $0.00217 |
| Haiku 4.5 | $0.00018 | $0.00109 |
Grade A, and why
commit-ko 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 24d 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
commit-ko — 커밋 메시지 자연화
한글 커밋 메시지 초안에서 AI 특유의 사무적·번역투 어휘만 걷어내고, 의미·범위·타입은 한 글자도 바꾸지 않는다.
입력
- 커밋 메시지 초안(subject 1줄 + 선택적 body). 여러 개면 각각 처리.
- Conventional Commits 형식(
type(scope): subject, 예:fix(auth): 로그인 실패 시 재시도 로직을 수행함)이면type/scope접두사는 그대로 두고, 콜론 뒤 한국어 부분만 윤문 대상으로 삼는다. - (선택) 사용자가
git diff나 변경 요약을 함께 주면 — 새 내용을 추가하기 위해서가 아니라, 윤문 과정에서 의미가 틀어지지 않았는지 대조 확인하는 용도로만 참고한다.
철칙 (humanize-korean과 동일 정신 계승)
- 의미·범위·타입 불변 — feat/fix/docs/refactor/chore 등 커밋 타입, 스코프, 무엇을 했는지의 사실관계는 절대 바꾸지 않는다.
- 새 내용 삽입 금지 — 원문에 없던 이유·효과·수치를 지어내지 않는다. 어휘·종결만 바꾼다.
- 과공손·과격식 방향으로도 바꾸지 않는다 — "~함" 같은 커밋 관용 종결이 이미 자연스러우면 "~하였습니다"로 격상시키지 않는다.
처리 절차
references/commit-lexicon.md를 읽는다.- 커밋 메시지에서 사무적 동사(수행/진행/실시 등)·한자어 명사화(-성/-적/-화)·과공손 종결·장황한 명사구 패턴과, 영어 직역 구문(by-passive "~에 의해", 이중 피동 "~되어지다", "가지고 있다"류 have 직역)을 찾는다. 단 업데이트·리팩터링·버그 등 개발 용어로 굳은 외래어는 대상이 아니다 — 어휘의 출신이 아니라 구문 구조가 문제다.
- 찾은 패턴만 lexicon의 처방대로 치환한다. 해당 패턴이 하나도 없으면 "이미 자연스러운 커밋 메시지입니다"라고 안내하고 종료한다(억지로 손대지 않음).
- type/scope 접두사, 이슈 번호, 파일·함수명 등 고유 토큰은 그대로 보존한다.
출력
- 윤문된 커밋 메시지 1개(원문과 형식을 맞춤 — subject만 있었으면 subject만).
- 애매한 경우 대안 표현을 1~2개까지 병기 가능.
- 무엇을 왜 바꿨는지 한 줄 근거(예: "'~을 수행함' → '~함' — 커밋 메시지에 불필요한 격식 동사").
참고
- 이 스킬의 치환표는
skills/humanize-korean/references/ai-tell-taxonomy.md의 A-7·A-8·A-9·A-12(번역투 구문)·F-4(한자어 명사화 -성/-적/-화) 처방을 커밋 메시지 register로 특화한 파생본이다(전체 ID 목록은references/commit-lexicon.md상단 참고). taxonomy가 갱신되면references/commit-lexicon.md도 함께 점검할 것 —python3 scripts/check_commit_lexicon_ids.py로 헤더-본문 ID 정합과 taxonomy 실재 여부를 검사할 수 있다. - 문단 단위 산문(리포트·칼럼·블로그 등)을 윤문할 때는 이 스킬이 아니라
humanize-korean을 쓴다.
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.
- 24d ago First seen · 46 lines · 183 tokens per session scan A 1d5ab962f236
commit-ko is a skill published in the GitHub repository epoko77-ai/im-not-ai (6,016 stars, last pushed 5d ago), licensed MIT. It adds 183 tokens to every session and 1,085 once invoked, about $0.0007 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 2026-09-23.
Other skills, from other repositories
humanizer-ru
A Russian-language editing guide that makes text sound more natural and less like it was produced by an AI system.
commit
Create well-structured git commits from the current working tree. Use when the user says 'commit', 'save my work', 'let's commit this', 'make a commit', or any variation of wanting to commit code to git.
humanizer-ru-local-edit-scope
Use when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice.
humanizer-ru-local-edit
Use when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice.
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
create-pr
Opens (or updates) a pull request with a conventional title, an evidence-backed description, and a real verification checklist — resolving the base branch from evidence, attaching screenshots via the GitHub CLI when the change is visible in the UI, and asking rather than guessing at every genuine judgment call. Use…