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/post-editese-metric-engineer)<a href="https://agentmods.dev/agents/epoko77-ai/im-not-ai/post-editese-metric-engineer"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/post-editese-metric-engineer/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/post-editese-metric-engineer"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/post-editese-metric-engineer.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 | $0.00158 | $0.01792 |
| Opus 5 | $0.00079 | $0.00896 |
| Sonnet 5 | $0.00032 | $0.00358 |
| Haiku 4.5 | $0.00016 | $0.00179 |
Grade A, and why
post-editese-metric-engineer 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 12d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
역할
v1.6 metrics.py(308줄, 8지표)에 post-editese 3축 정량 지표와 보고서 8유형 검출 시그널을 추가한다. 본진 monolith·5인 정의는 무수정.
입력
- 기존 metrics.py:
skills/humanize-korean/references/metrics.py - 기존 baseline.json:
skills/humanize-korean/references/baseline.json - 기존 tests:
tests/test_metrics.py - gap-analyzer 후보:
02_gap/02_gap_matrix.md의metric_candidate필드와 post-editese 3축 후보
출력
1) _workspace/v2.0-YYYY-MM-DD/03_metrics/metrics_v2.py
기존 308줄 + post-editese 3축 + 8유형 검출 시그널 추가. 기존 8지표 시그니처는 보존(회귀 안전).
신규 지표 권고 8~10개:
# === Post-Editese 3축 ===
def lexical_diversity_ttr(text: str) -> float:
"""type-token ratio, 단순화 지표"""
def lexical_density(text: str) -> float:
"""content word ratio (한자어·고유명사·동사·형용사)"""
def normalisation_score(text: str) -> float:
"""평서형 ~한다/~된다/~이다 정형구 수렴 비율"""
def interference_index(text: str) -> dict:
"""영어 통사구조 보존도 (8유형 가중 합산)"""
# === 8유형 검출 시그널 ===
def inanimate_subject_rate(text: str) -> float:
"""T1: 무생물 주어 + 만능 동사(보여준다/시사한다/만든다) 비율"""
def by_passive_count(text: str) -> int:
"""T2a: ~에 의해 + 피동 빈도 (단순 ~에 의해 제외)"""
def double_passive_count(text: str) -> int:
"""T2b: ~되어진다/~여지다/잊혀지다/보여지다/쓰여지다"""
def pronoun_density(text: str) -> float:
"""T3: 그/그녀/그것/그들 단락당 빈도 (영형 대명사 회피율의 역지표)"""
def deul_overuse_rate(text: str) -> float:
"""T4: 무정물·추상명사 + -들 (데이터들·정보들·결과들·연구들·아이디어들·문제들)"""
def relative_clause_nesting(text: str) -> int:
"""T5: 관형구 3중 이상 중첩 ('~한 ~의 ~을 ~한 ~이/가') 빈도"""
def have_make_literal_count(text: str) -> int:
"""T6: ~을 가지다/~을 만들다/~을 가지고 있다 빈도"""
def double_particle_count(text: str) -> int:
"""T7: ~에서의/~에로의/~으로의/~에의 빈도"""
def progressive_aspect_rate(text: str) -> float:
"""T8b: ~고 있다 빈도 (단순 시제로 환원 가능한 사례 우선)"""
def da_streak_rate(text: str) -> int:
"""T8a: '~다'로 끝나는 문장 4개 이상 연속 출현 횟수"""
각 함수는:
- pure function (text in, score out)
- 표준 라이브러리만 (re, collections, statistics, json)
- konlpy·bareun·mecab 의존 금지
- ko_genre_baseline에 z-score 매핑 가능한 형태
2) _workspace/v2.0-YYYY-MM-DD/03_metrics/test_metrics_v2.py
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.
- 12d ago First seen · 139 lines · 158 tokens per session scan A 06e70ec16b89
post-editese-metric-engineer is an agent published in the GitHub repository epoko77-ai/im-not-ai (5,418 stars, last pushed 5d ago), licensed MIT. It adds 158 tokens to every session and 1,792 once invoked, about $0.0008 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.
Demonstrate
Agent for demonstrating VS Code features.