translationese-research-distiller

translationese-research-distiller is an agent for Claude Code from epoko77-ai/im-not-ai. It costs 198 tokens per session (1,533 once invoked), scanned A, original, MIT.

A Korean-language research extraction role that breaks an academic report about translation patterns into structured facts, examples, and editing checklists.

In plain words
What is it for?
It is for extracting translation types, post-editing checks, academic references, and example sentences from a specified report.
Why use it?
It gives later steps organized material while limiting them to claims explicitly stated in the report.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the humanize-korean plugin — 3 skills, 9 agents shipped together

Good fit It is for extracting translation types, post-editing checks, academic references, and example sentences from a specified report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/epoko77-ai/im-not-ai/translationese-research-distiller
About the project

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.

epoko77-ai/im-not-ai · 5,459 stars · on GitHub · imnotai.kr

Install

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.

Clone the repo
git clone --depth 1 https://github.com/epoko77-ai/im-not-ai

Made for: Claude Code.

Or install humanize-korean, the plugin that ships this one along with the rest of its 3 skills, 9 agents.

Wrote 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.

agentmods badge for translationese-research-distiller

README.md
[![agentmods](https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/translationese-research-distiller/github.svg)](https://agentmods.dev/agents/epoko77-ai/im-not-ai/translationese-research-distiller)
Your own site
<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.

agentmods 80×15 button for translationese-research-distiller

Your own site · 80×15
<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>
Per session 198 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 13d ago against content hash 41498658b18f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agents/translationese-research-distiller.md · 85 lines

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)"
  ]
}

Read the full file on GitHub · 85 lines

Changes

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.

  1. 13d ago First seen · 85 lines · 198 tokens per session scan A 41498658b18f

Subscribe to this mod's changes

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.

Related

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…

devswha/patina · 81 tokens

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…

devswha/patina · 80 tokens

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.

devswha/patina · 76 tokens

chapter-synthesis-editor

Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.

equinor/neqsim · 28 tokens

shaman

Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.

pjt222/agent-almanac · 29 tokens

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.

smicolon/ai-kit · 46 tokens