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 humanize-redogit 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/humanize-redo)<a href="https://agentmods.dev/skills/epoko77-ai/im-not-ai/humanize-redo"><img src="https://agentmods.dev/badge/skills/epoko77-ai/im-not-ai/humanize-redo/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/humanize-redo"><img src="https://agentmods.dev/badge/skills/epoko77-ai/im-not-ai/humanize-redo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00595 |
| Opus 5 | $0.00037 | $0.00298 |
| Sonnet 5 | $0.00015 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
humanize-redo 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.
What it actually says
/humanize-redo — 2차 윤문 / 부분 재실행
cwd 기준 가장 최근 _workspace/{run_id}/를 찾아 humanize-korean 스킬의 strict 윤문(Phase B)부터 재호출한다.
사용자 지시
$ARGUMENTS
동작
Glob으로_workspace/YYYY-MM-DD-*/final.md(또는01_input.txt)를 매칭해 최신run_id식별. 없으면 "이전 실행이 없습니다./humanize로 시작하세요" 안내 후 종료.- 사용자 지시 파싱:
- 카테고리 지정("번역투만", "관용구만", "이모지만") → 해당 카테고리 finding만 재윤문
- 문단 지정("이 문단만", "두 번째 문단만") → 해당 범위 finding만
- 강도 조정("강도 낮춰"·"보수적으로" → S1만, "강도 높여" → S1+S2+S3)
- 롤백 요청("이 변경 되돌려줘") → 해당 edit을
content-fidelity-auditor롤백으로 처리 - 지시 없음·"2차 윤문해줘" → 잔존 finding 전체 대상 round 2
korean-style-rewriter재호출 입력: 기존02_detection.json또는05_naturalness_review.json의 잔존 finding + 사용자 지시를target_filter로 전달.- 산출물은
03_rewrite_v2.md(또는 v3)로 버전 분리. 이전final.md는final_prev.md로 백업. - strict Phase C 병렬 검증 → Phase D 최종 출력(변경 비교 표 + 신규 등급).
루프 한도
최대 round 3. 그 이상 미해결이면 hold_and_report로 사람 검토 권고.
참고
- 풀 파이프라인 신규 실행은
/humanize. - 분류 체계:
humanize-korean/references/ai-tell-taxonomy.md
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 · 33 lines · 75 tokens per session scan A df556584d322
humanize-redo is a skill published in the GitHub repository epoko77-ai/im-not-ai (5,418 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 595 once invoked, about $0.0004 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
humanizer-ru
A Russian-language editing guide that makes text sound more natural and less like it was produced by an AI system.
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.
humanizer-zh-tw
A writing-editing skill for making Traditional Chinese text sound more like it was written by a person.
patina
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese text so it reads as if a human wrote it. Meaning-preservation (MPS) verified.
patina-aside
Use Patina's local options page and verified CLI rewrite when drafting or revising blog posts in Aside, including automatic blog workflows.