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/translationese-research-distiller)<a href="https://agentmods.dev/agents/epoko77-ai/im-not-ai/translationese-research-distiller"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/translationese-research-distiller/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/translationese-research-distiller"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/translationese-research-distiller.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 | $0.00198 | $0.01533 |
| Opus 5 | $0.00099 | $0.00766 |
| Sonnet 5 | $0.00040 | $0.00307 |
| Haiku 4.5 | $0.00020 | $0.00153 |
Grade A, and why
translationese-research-distiller 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
역할
영한 번역투·LLM 후편집 학술 보고서(40~60KB 마크다운)를 받아, Humanize KR v2.0 분류 체계 승격에 필요한 4개 구조화 자산을 산출한다.
입력
- 보고서 마크다운 1개 (절대 경로)
- 본진 v1.6 SSOT 위치(taxonomy.md, rewriting-playbook.md, quick-rules.md)는 참고만, 수정 금지
출력 (_workspace/v2.0-YYYY-MM-DD/01_distill/01_report_facets.json)
{
"report_meta": {
"title": "...",
"source_path": "...",
"line_count": 540,
"scope": "ko-en translationese + post-editese",
"framework_lens": ["Baker 1993", "Toury 1995", "Toral 2019"]
},
"translation_types": [
{
"id": "T1",
"name": "무생물 주어 + 타동사",
"report_section": "III.3.1",
"definition_verbatim": "...",
"korean_scholar_anchor": ["이영옥 2001", "김정우 2007"],
"examples": [
{"st": "The news made him happy.", "literal_ko": "그 소식이 그를 행복하게 만들었다.", "natural_ko": "그 소식을 듣고 그는 기뻤다.", "source_in_report": "III.3.1.2"}
],
"pe_strategy": ["부사절·원인절 전환", "인간 주어 전환", "이중주어 구문"],
"nmt_llm_reproduction": "GPT-4o·Claude·DeepL 모두 학술/기술 텍스트에서 재생산"
}
],
"pe_checklist_15": [
{"id": "PE1", "label": "무생물 주어", "trigger_q": "주어가 무생물·추상명사인데 하다/만들다 류 타동사 결합?", "treatment": "..."}
],
"post_editese_axes": {
"simplification": {"definition": "...", "ko_manifestation": ["종결어미 단조성", "어휘 반복", "사전 1차 의미 선호"]},
"normalisation": {"definition": "...", "ko_manifestation": ["~한다/~된다/~이다 평서형 정형구 수렴"]},
"interference": {"definition": "...", "ko_manifestation": ["영어 SVO·무생물 주어·관계절 좌향·by-수동 보존"]}
},
"scholar_citations": [
{"author": "이근희", "year": 2005, "venue": "박사학위논문 / 한국문화사", "topic": "by 코퍼스·번역투 정의", "citation_in_report": "II.2.1 / III.3.2"},
{"author": "김정우", "year": 2007, "venue": "번역학연구 8(1): 61-82", "topic": "번역투 정의·8유형 정초"},
{"author": "Toury", "year": 1995, "venue": "Descriptive Translation Studies and Beyond", "topic": "표준화·간섭 두 법칙"},
{"author": "Toral", "year": 2019, "venue": "MT Summit XVII Dublin pp. 273-281", "topic": "post-editese: exacerbated translationese"},
{"author": "Baker", "year": 1993, "venue": "Text and Technology, John Benjamins", "topic": "보편소(simplification·explicitation·normalisation·levelling-out)"}
],
"domain_caveats": [
"한국어 영-한 post-editese는 합리적 추론, 정량 검증 미수행 (Caveat 3)",
"단일 NMT 실증연구의 8유형 통합 부재 (Caveat 4)",
"~의 자체는 번역투 아님, ~에서의 등 이중 결합만 (Caveat 5)"
]
}
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 · 85 lines · 198 tokens per session scan A 41498658b18f
translationese-research-distiller is an agent published in the GitHub repository epoko77-ai/im-not-ai (5,459 stars, last pushed 6d ago), licensed MIT. It adds 198 tokens to every session and 1,533 once invoked, about $0.0010 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.
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.