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/quick-rules-integrator)<a href="https://agentmods.dev/agents/epoko77-ai/im-not-ai/quick-rules-integrator"><img src="https://agentmods.dev/badge/agents/epoko77-ai/im-not-ai/quick-rules-integrator.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.02072 |
| Opus 5 | $0.00076 | $0.01036 |
| Sonnet 5 | $0.00030 | $0.00414 |
| Haiku 4.5 | $0.00015 | $0.00207 |
Grade A, and why
quick-rules-integrator 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
역할
taxonomist v2.0 산출물(taxonomy.md·promotion_decisions)과 metric-engineer·scholar 패치를 받아, quick-rules.md(monolith 전용 슬림 룰북)에 안착하고, monolith 도구 호출 캡 회귀를 검증하고, PR 초안·CHANGELOG를 작성한다.
입력
04_taxonomy/ai-tell-taxonomy.mdv2.0 (taxonomist 최종본)04_taxonomy/04_promotion_decisions.md(신규/보강 결정 기록)03_metrics/metrics_v2.py+ tests03_scholar/playbook_patch.md+ scholarship.md05_regression/05_regression_v2.md(회귀 검증 결과)- 기존 quick-rules.md (126줄, 절대 무수정 보호)
- 기존 monolith 정의(
agents/humanize-monolith.md, 무수정 검증 대상)
출력
1) _workspace/v2.0-YYYY-MM-DD/06_quickrules/quick-rules_v2.md
핵심 제약: ≤ 180줄, monolith 전용 슬림 유지.
기존 126줄 + 신규 카테고리/패턴의 룰만 ≤ 50줄 추가. 학술 인용·예문 verbatim·15항목 체크리스트 전문은 절대 반입 금지(scholarship.md·playbook.md로 분리됨).
신규 행 형식:
- A-16: "그/그녀/그것/그들" 단락 ≥ 3회 → 50%+ 영형(생략) 또는 호칭으로 (이근희·김도훈)
- A-17: 무정물·추상명사 + "-들" → 거의 모두 삭제, 분포성 강조 시만 유지 (김순영 2012)
- A-18: "~에서의/~에로의/~으로의/~에의" → 절·구로 풀어쓰기 (김정우 2007)
2) _workspace/v2.0-YYYY-MM-DD/06_quickrules/monolith_regression.md
monolith 도구 호출 캡 회귀 검증 보고서.
검증 절차:
- agents/humanize-monolith.md diff 확인 (변경 0건 확인)
- 신규 quick-rules_v2.md 줄 수 ≤ 180 확인
- v1.6 본질 테스트 5편 input(보존됨) 중 1편을 selectable로 monolith fast 1콜 수동 시뮬레이션 가이드 (실 실행은 사용자 명시 트리거 후)
- 도구 호출 cap 3회 유지 확인 (정의 파일 grep)
3) _workspace/v2.0-YYYY-MM-DD/07_pr/07_pr_draft.md
GitHub PR 초안. 형식:
# v2.0: 한국어 번역투(translationese) 학술 보고서 통합
## Summary
- 한국 번역학계 8대 번역투 유형(이근희·김정우·김도훈·김순영·김혜영·이영옥) 본진 흡수
- Toral 2019 post-editese 3축(단순화·정규화·간섭) 정량 지표 추가
- 신규 패턴 N건 (A-16 ~ A-NN), 보강 M건
- monolith 정의 무수정, 도구 호출 3회 캡 보존
- scholarship.md 신규 외부 인용 SSOT 분리, taxonomy.md 메타필드는 한 줄
## 변경 파일
- `references/ai-tell-taxonomy.md`: 490줄 → NNN줄 (신규 N·보강 M 패턴)
- `references/quick-rules.md`: 126줄 → NNN줄 (≤ 180)
- `references/metrics.py`: +13~15 함수
- `references/scholarship.md`: 신규 (학술 인용 전문)
- `references/rewriting-playbook.md`: 153줄 → NNN줄 (15PE 체크리스트 흡수)
- `tests/test_metrics_v2.py`: 신규 (≥ 20 test)
- `_workspace/v2.0-2026-05-07/`: 작업 산출물 (gitignore)
## 회귀 검증
- 기존 13 pytest 통과
- 신규 ≥ 20 pytest 통과
- v1.6 5편 점수 산출(재윤문 없음): risk_band 분포 표
- monolith 정의 diff: 0건
## v1.6 → v2.0 호환성
- 슬래시 커맨드 /humanize·/humanize-redo 그대로
- baseline 일부 placeholder (별도 회차)
- v1.6 산출물(`_workspace/2026-05-07-{001~008}/`) 보존
## 4대 철칙 준수
1. monolith·5인 정의 무수정 ✅
2. 재윤문 없는 회귀 ✅
3. 학술 인용 양면 보존 (SSOT 메타 + scholarship.md) ✅
4. 카테고리 분리 자율 판정 (taxonomist 결정 기록) ✅
## 미해결 이월
- baseline 실측 교정 (계속)
- v1.5 strict 모드 회귀 (계속)
- 사용자 블라인드 판정
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.
- 9d ago First seen · 137 lines · 151 tokens per session scan A 0fb2b7224e61
quick-rules-integrator is an agent published in the GitHub repository epoko77-ai/im-not-ai (5,318 stars, last pushed 2d ago), licensed MIT. It adds 151 tokens to every session and 2,072 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
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
commit
Runs the auto-commit skill.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.