im-not-ai: Instructions file for Gemini CLI

GEMINI.md

im-not-ai GEMINI.md is an instructions file for Gemini CLI from epoko77-ai/im-not-ai. It costs 3,213 tokens per session, scanned A, original, MIT.

A Gemini CLI extension for rewriting Korean AI-generated text so it reads more naturally while preserving its facts, claims, numbers, names, and quotations. It combines detection, editing, and self-checking in one conversation.

In plain words
What is it for?
Use commands such as /humanize-korean or /humanize to revise Korean writing, and /humanize-redo to run another targeted edit.
Why use it?
It removes translation-like wording, repetitive structures, excessive connectors, and other AI-writing patterns without changing the text’s meaning or level of formality.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Claude Code; mentions Gemini CLI.

This is epoko77-ai/im-not-ai's own configuration. It tells Gemini CLI how to work on im-not-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything im-not-ai configures →

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 · 5,355 stars · on GitHub · imnotai.kr

Reuse

Borrowing it

Nothing to install: this file belongs to epoko77-ai/im-not-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/epoko77-ai/im-not-ai/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/epoko77-ai/im-not-ai

Made for: Gemini CLI.

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 im-not-ai GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/epoko77-ai/im-not-ai/gemini-md/github.svg)](https://agentmods.dev/instructions/epoko77-ai/im-not-ai/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/epoko77-ai/im-not-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/epoko77-ai/im-not-ai/gemini-md/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 im-not-ai GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/epoko77-ai/im-not-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/epoko77-ai/im-not-ai/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,213 This file is loaded in full into every session.
When invoked 3,213 The same file — it is already loaded in full.
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 $0.03213 $0.03213
Opus 5 $0.01606 $0.01606
Sonnet 5 $0.00643 $0.00643
Haiku 4.5 $0.00321 $0.00321

Measured 3d ago against content hash 2c4c09731101, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

im-not-ai GEMINI.md 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 3d 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.

GEMINI.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanize KR — AI 한글 티 제거 (Gemini CLI Extension)

v1.5 · Fast(monolith) 모드 전용 — Gemini CLI에서 한 번의 대화로 탐지·윤문·자체검증을 일괄 처리합니다. 정밀 3콜(진단→겨냥 윤문→finalize)은 Claude Code 전용입니다.

개요

AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문합니다. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 재작성합니다.

커스텀 명령

  • /humanize-korean [텍스트] — 메인 윤문 명령
  • /humanize [텍스트]/humanize-korean과 동일
  • /humanize-redo [조정 지시] — 2차 윤문 / 부분 재실행

자연어 트리거도 동작합니다: "이 글 AI 티 없애줘", "AI 윤문", "ChatGPT 티 제거", "번역투 고쳐", "사람이 쓴 것처럼".

철칙 (위반 시 즉시 롤백)

  1. 의미 불변 (Fidelity First) — 사실·주장·수치·고유명사·인용은 100% 원문 보존.
  2. 근거 기반 (Span-Grounded) — 아래 패턴 목록에 매핑되지 않는 구간은 건드리지 않음.
  3. 장르 유지 (Tone Match) — 칼럼을 문학으로, 리포트를 에세이로 옮기지 않음.
  4. register 보존 — 원문 격식체면 결과도 격식체. AI 티는 문법·수사이지 격식 자체가 아님.
  5. 과윤문 금지 — 변경률 30% 초과 시 경고, 50% 초과 시 강제 중단.

Do-NOT (탐지·윤문 모두 제외)

고유명사·제품명·모델명·기관명, 수치·날짜·단위, 큰따옴표 안 직접 인용, 법률 조문, 수학·화학·통계 표기, 영어 약어(LLM·GPU·MCP·API 등 업계 표준).

절차

  1. 입력 확보: 사용자가 붙여넣은 텍스트를 원문으로 한다. 파일 경로(.txt/.md)면 그 파일을 읽는다.
  2. 장르 추정: 첫 300자로 장르 추정(사용자 명시 시 우선). 칼럼 | 리포트 | 블로그 | 공적.
  3. 탐지: 아래 A~J 카테고리 패턴을 스캔해 (ID, span, severity, fix) 수집. Do-NOT span은 제외.
  4. 윤문: D(관용구 삭제) → A → I → G → H → F → B → C·J → E 순서로 문단 단위 처리.
  5. 자체검증: 아래 체크리스트 6항 점검. 위반 시 해당 edit 롤백 → 부분 재실행(최대 1회).
  6. 출력: 윤문본 + 메트릭 요약 반환.

응답 형식

사용자에게 4가지 반환:

  1. 한 줄 상태: 완료. 변경률 X% / 등급 Y / 자체검증 N/6 통과
  2. 윤문본 본문 (마크다운 블록)
  3. 카테고리별 탐지 건수 before/after + 주요 변경 하이라이트 3~5건
  4. 등급 B 이하면 "정밀 검증이 필요하면 Claude Code의 정밀 모드(3콜) 권장" 안내

옵션 (인자 끝에 자연어로)

  • 장르: 칼럼|리포트|블로그|공적 — 장르 명시 (생략 시 자동 추정)
  • 강도: 보수|기본|적극 — 윤문 강도 (기본값: 기본)
  • 최소심각도: S1|S2|S3 — 탐지 임계값 (기본값: S2)

AI 티 패턴 목록 (Quick Rules)

A. 번역투 (Translation-ese)

ID 패턴 심각도 처방
A-1 "~에 대해(서)" S1 목적격 조사로 직결("X에 대해 논의" → "X를 논의")
A-2 "~를 통해/통하여" 남발 S1 "~로", "~해서", "~함으로써"로 분산
A-3 "~에 있어(서)" S1 "~에서", "~을 볼 때"
A-4 "~라는 점에서" 3회+ S2 "~서", "~라는 이유로"
A-5 "~와 관련하여/관련된" S2 "~에", "~의"
A-6 "~에 기반하여/바탕으로" 남발 S2 "~로", "~을 보고"
A-7 "가지고 있다" / have·make·take·give + N 직역 S1 형용사·동사 환원
A-8 이중 피동 "~되어진다" S1 능동 또는 단일 피동
A-9 "~에 의해" 피동 S2 행위자를 주어로
A-10 "~할 수 있다" 남발 S2 단언으로
A-11 "~을 위해" 목적절 남발 S2 "~려고", "~위한"
A-15 추상 주어 + 만능 동사 S2 구체 주어로 환원
A-16 대명사 출현마다 직전 2문장 선행 후보 수(빈도 임계 없음) S1 후보 0개 → 명사구 복원 / 1개 → 영형 / 2개+ → 명사구 되짚기. 불확실하면 유지
A-18 명사 앞 ≥3어절 관형구 S2 문장 분리 또는 후치 동격절
A-19 이중 조사 "~에서의/~에로의" S2 절·구로 풀어쓰기

Read the full file on GitHub · 180 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. 3d ago Changed · +29 tokens per session 2c4c09731101
  2. 10d ago First seen · 180 lines · 3,184 tokens per session scan A 9098cddc9832

Subscribe to this mod's changes

im-not-ai GEMINI.md is an instructions file published in the GitHub repository epoko77-ai/im-not-ai (5,355 stars, last pushed 3d ago), licensed MIT. It adds 3,213 tokens to every session, about $0.0161 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens