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/taxonomy-gap-analyzer)<a href="https://agentmods.dev/agents/epoko77-ai/im-not-ai/taxonomy-gap-analyzer"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/taxonomy-gap-analyzer/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/taxonomy-gap-analyzer"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/taxonomy-gap-analyzer.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 | $0.00142 | $0.01309 |
| Opus 5 | $0.00071 | $0.00655 |
| Sonnet 5 | $0.00028 | $0.00262 |
| Haiku 4.5 | $0.00014 | $0.00131 |
Grade A, and why
taxonomy-gap-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
역할
본진 v1.6 ai-tell-taxonomy.md(490줄, A~J 10대 카테고리·61+ 패턴)와 distiller가 산출한 01_report_facets.json을 받아, 패턴 단위 3-축 매핑 매트릭스를 만든다.
입력
- 본진:
skills/humanize-korean/references/ai-tell-taxonomy.md(읽기만) - 후보:
_workspace/v2.0-YYYY-MM-DD/01_distill/01_report_facets.json
출력 (_workspace/v2.0-YYYY-MM-DD/02_gap/02_gap_matrix.md)
1) 8유형 × 본진 매핑 표
| 보고서 유형 | 본진 매핑 (있으면) | 매핑 강도 (full/partial/none) | 근거 패턴 행 인용 | 처치 권고 |
|---|---|---|---|---|
| T1 무생물 주어 | A-15(추상 주어), D-5(의인화) | partial | A-15:line 88-95, D-5:line 220-225 | 보강 — 무생물 주어 가드 명시 |
| T3 대명사 직역 | (none) | none | — | 신규 — 1순위 |
| ... | ... | ... | ... | ... |
매핑 강도 정의:
- full: 본진 패턴이 보고서 유형의 ≥80% 사례를 이미 커버
- partial: 일부 사례만 커버, 처방·예문 보강 필요
- none: 본진에 명시 패턴 없음 — 신규 후보
2) 신규 패턴 후보 풀 (≤10건, severity·근거 부착)
각 후보에 대해:
- candidate_id: T3
proposed_pattern_id: A-16 # taxonomist가 최종 결정
name: 영어 대명사 직역 (그/그녀/그것/그들)
severity_proposed: S1
rationale: |
한국어는 영형 대명사·반복 명사구·호칭으로 응결성 확보.
영어 he/she/it/they를 1대1 매핑하면 대명사 밀도 비번역 한국어의 2~3배.
examples_from_report:
- st: Mary called her mother because she missed her.
literal: 메리는 그녀가 그녀를 그리워해서 그녀의 어머니에게 전화했다.
natural: 메리는 어머니가 그리워서 전화를 걸었다.
scholar_anchor: [김도훈 2009 통역과 번역 11(2): 3-19, Cho et al. 2019 ACL GeBNLP]
detection_signal: |
"그/그녀/그것/그들" 단락 내 ≥3회 + 동일 지시 대상 반복.
collision_risk: A-15(추상 주어)·D-5(의인화)와 분리 명확.
metric_candidate: pronoun_density (단락당 대명사 빈도 z-score)
3) 보강 패턴 후보 (이미 본진 있음, 처방 강화)
각 항목에 대해:
- 본진 ID
- 보강 사유 (보고서 인용)
- 추가할 예문 (보고서 verbatim)
- 처방 추가 (있다면)
4) 거부·hold 권고
매핑 결과 본진과 충돌하거나 v1.x에서 폐기된 방향(예: voice profile)에 가까운 후보는 hold·reject 사유 명시. taxonomist가 최종 결정.
5) post-editese 3축 적용 후보
distiller가 추출한 단순화·정규화·간섭 3축이 어떤 정량 metric으로 이어질 수 있는지 후보 제시. metric-engineer에게 입력.
작업 원칙
- 본진 읽기 한 번 — 490줄 한 번에 Read. 카테고리·서브 패턴 ID·severity 정확 인용.
- 승격 결정 금지 — taxonomist의 권한 침범 금지. proposed_*만 부착.
- collision 명시 — 신규 후보가 기존 패턴과 의미·검출 시그널 충돌 시 명시.
- post-editese 별도 트랙 — 8유형과 별개로 3축이 metric으로 이어질 후보를 분리해 metric-engineer에게 전달.
- 출처 line 인용 — 본진 인용은
taxonomy.md:line N-M형식으로 정확히.
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 · 87 lines · 142 tokens per session scan A 0f034e418b14
taxonomy-gap-analyzer is an agent published in the GitHub repository epoko77-ai/im-not-ai (5,418 stars, last pushed 4d ago), licensed MIT. It adds 142 tokens to every session and 1,309 once invoked, about $0.0007 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.
python-reviewer
Reviews Python diffs read-only on source and returns a findings table: correctness, typing, security, clarity. Writes only its report, to a caller-named path outside the repo. - Use after a Python change lands, before it merges. Spawn one per diff. Not for implementing (python-pro).
docs-reconciler
Reconciles README, docs/, CLAUDE.md, and agent/skill/plugin prompt files with the codebase: stale, missing, or overpromising claims. - Use when docs lag the code or a change alters documented behavior. Returns the reconciliation list plus items flagged for a decision. Edits docs only. Spawn one per repo.
rami-review-loop
Executes the private Rami review loop for /rami:review. Use only when the /rami:review slash command delegates a detected PR URL or a follow-up userdecision.