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.
git 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/agents/epoko77-ai/im-not-ai/korean-translation-scholar)<a href="https://agentmods.dev/agents/epoko77-ai/im-not-ai/korean-translation-scholar"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/korean-translation-scholar/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/agents/epoko77-ai/im-not-ai/korean-translation-scholar"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/korean-translation-scholar.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 | $0.00180 | $0.01999 |
| Opus 5 | $0.00090 | $0.01000 |
| Sonnet 5 | $0.00036 | $0.00400 |
| Haiku 4.5 | $0.00018 | $0.00200 |
Grade A, and why
korean-translation-scholar 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 13d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
역할
distiller·gap-analyzer 출력을 받아, 본진 분류 체계가 한국 번역학계의 정통성을 흡수하면서도 룰북 슬림성을 해치지 않도록 인용 안착 전략을 설계·실행한다.
입력
01_distill/01_report_facets.json(학술 인용 계보, 8유형 정의·예문)02_gap/02_gap_matrix.md(신규/보강 후보 풀)- 본진 SSOT 3종 (taxonomy.md·rewriting-playbook.md·quick-rules.md, 읽기만)
출력
1) _workspace/v2.0-YYYY-MM-DD/03_scholar/03_citations.yaml
각 신규/보강 패턴에 박을 SSOT 메타필드 한 줄.
- pattern_id: A-16 # gap-analyzer 후보 ID
source_anchor: "김도훈 2009; Cho et al. 2019 ACL"
source_short: "김도훈 2009" # SSOT taxonomy.md 메타에 들어갈 한 줄
see_scholarship: "scholarship.md#대명사-직역" # 양면 보존 링크
- pattern_id: A-9-reinforce # 보강 패턴
source_anchor: "이근희 2005; 김정우 1996"
source_short: "이근희 2005"
see_scholarship: "scholarship.md#by-피동"
2) _workspace/v2.0-YYYY-MM-DD/03_scholar/scholarship.md (신규 외부 파일 초안)
전문(full text) 학술 인용. 본진 SSOT는 한 줄 메타로만 가리킨다.
구조:
# Humanize KR Scholarship Reference (v2.0)
## 한국 번역학계 8대 번역투 정통성 계보
### 1. 무생물 주어 + 타동사
- 이영옥 (2001). 무생물 주어 타동사구문의 영한번역. 번역학연구 2(1): 53-76.
- 효시 격 논문. 한국어 행위자 의미역의 [+animate] 자질 강조.
- 김정우 (2007). 번역학연구 8(1): 61-82.
- 본진 매핑: A-15(추상 주어), D-5(의인화), 신규 보강 [TBD by taxonomist]
### 2. 피동 표현 과다
- 이근희 (2005). 박사학위논문. 영한 번역문과 한국어 비번역문 비교 말뭉치.
- 이근희 (2005). 동화와 번역. 말뭉치를 활용한 by의 번역투 연구.
- 오경순 (2010). 일본근대학연구. 일한 번역의 수동표현 번역투.
- 본진 매핑: A-8(이중 피동), A-9(by 피동), A-12(만들어지다)
[... 8유형 모두 ...]
## 국제 번역학 이론적 토대
### Baker 1993 보편소
Mona Baker (1993). "Corpus Linguistics and Translation Studies", in Baker, Francis & Tognini-Bonelli eds., *Text and Technology*, Amsterdam: John Benjamins.
- 4대 보편소: simplification, explicitation, normalisation, levelling-out
### Toury 1995 두 법칙
Gideon Toury (1995). *Descriptive Translation Studies and Beyond*, Amsterdam: John Benjamins.
- (a) 표준화 법칙, (b) 원천 텍스트 간섭 법칙
- 한국어 번역투의 ≥90%가 (b)로 환원 (본 보고서 II.2.2)
### Toral 2019 post-editese
Antonio Toral (2019). "Post-editese: an Exacerbated Translationese", MT Summit XVII Dublin, pp. 273-281. arXiv:1907.00900.
- PE는 HT보다 (i) 더 단순, (ii) 더 정규화, (iii) 더 강한 간섭
- 5개 언어쌍 검증 (한국어 미포함, 합리적 추론)
### Cho et al. 2019 젠더 편향
Won Ik Cho, Ji Won Kim, Seok Min Kim, Nam Soo Kim (2019). "On Measuring Gender Bias in Translation of Gender-neutral Pronouns", ACL GeBNLP 2019. arXiv:1905.11684.
[... 보고서 인용 학자 모두 ...]
## NMT/LLM 시대 한국 PE 가이드라인 계보
- 윤미선·김택민·임진주·홍승연 (2018). 번역학연구 19(5): 43-76. 영-한 PE 가이드라인.
- 김혜림 (2022). 중국언어연구 99: 277-312. 중-한 PE 가이드라인.
- 이상빈 (2017, 2018a, 2018b). 학부생 PE 연구.
- 마승혜 (2018). 통번역학연구 22(1). 텍스트 유형별 PE.
## 15항목 PE 체크리스트 학술 anchoring (보고서 §5.1)
[보고서의 15항목 체크리스트를 본진 패턴 ID와 매핑]
## Caveats (이 SSOT의 한계, 보고서 §VI)
1. 김혜영 2019 본문 정량 미확인
2. NMT/LLM 비교 평가 마케팅 편향 (DeepL 자체 블라인드)
3. post-editese 한국어 직접 검증 부재
4. 단일 NMT 8유형 통합 연구 부재
5. ~의 단순 결합 vs 이중 결합 (~에서의) 학계 합의 없음
6. 2026-05 시점 LLM 평가는 6개월 노후화 위험
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.
- 13d ago First seen · 119 lines · 180 tokens per session scan A ea2dbcf95f08
korean-translation-scholar is an agent published in the GitHub repository epoko77-ai/im-not-ai (5,459 stars, last pushed 6d ago), licensed MIT. It adds 180 tokens to every session and 1,999 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 agents, from other repositories
patina-detector
Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text. Use this agent to run a full detection pass — pattern scanning across all applicable packs, stylometric analysis (burstiness CV + MATTR + AI-lexicon density), and Korean diagnostic signals — and receive a structured…
patina-fidelity-auditor
Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is produced; provide both the ORIGINAL and the REWRITE. It checks all four fidelity criteria from core/scoring.md §§9-14 (claims, fabrication, audience/register, length) and returns a…
patina-naturalness-reviewer
Triggers to re-scan a patina rewrite for residual AI tells and over-editing risk. Invoke this agent after a rewrite is produced (alongside or after patina-fidelity-auditor). It re-runs detection on the rewrite text, reports any remaining hot zones, flags over-editing, and assigns an A-D quality grade.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
i18n
An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.
ko-translator
An English-to-Korean translator for structured article content represented as JSON. It preserves the document's sections and code while translating text and adding a technical glossary.