humanize

humanize is a skill for Claude Code from epoko77-ai/im-not-ai. It costs 73 tokens per session (537 once invoked), scanned A, original, MIT.

A command for making AI-written Korean text sound more natural through an automated editing process.

In plain words
What is it for?
Use it to edit pasted Korean text or text files, choose a genre and editing strength, and receive change rates, issue counts, highlights, and a revised version.
Why use it?
It gives Korean writing a structured review and revision pass, with a faster default mode or a stricter multi-step mode.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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

Good fit Use it to edit pasted Korean text or text files, choose a genre and editing strength, and receive change rates, issue counts, highlights, and a revised version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/epoko77-ai/im-not-ai/humanize
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 · 5,418 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.

Any agent
npx skills add epoko77-ai/im-not-ai --skill humanize
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 humanize

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/epoko77-ai/im-not-ai/humanize"><img src="https://agentmods.dev/badge/skills/epoko77-ai/im-not-ai/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 537 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00073 $0.00537
Opus 5 $0.00036 $0.00269
Sonnet 5 $0.00015 $0.00107
Haiku 4.5 $0.00007 $0.00054

Measured 11d ago against content hash 098277d12814, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

humanize 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.

skills/humanize/SKILL.md · 36 lines

What it actually says

/humanize — 한글 AI 티 제거

humanize-korean 스킬을 발동해 인자로 전달된 한글 텍스트(또는 파일)에 윤문을 실행한다.

입력

$ARGUMENTS

동작

  1. 인자가 비면: "윤문할 텍스트를 붙여넣어 주세요" 안내 후 종료.
  2. 인자가 파일 경로(.txt/.md)면 Read로 본문 로드.
  3. 인자가 텍스트면 그대로 입력으로 사용.
  4. humanize-korean 스킬 SKILL.md 절차(Phase 0 → 결과 전달)를 따른다 — 기본 Fast 모드, --strict 시 정밀 3콜(진단→겨냥 윤문→finalize).
  5. 결과 전달:
    • 한 줄 상태(변경률 / 등급 / 자체검증 통과)
    • 윤문본 본문(마크다운 블록)
    • 카테고리별 탐지 건수 before/after
    • 주요 변경 하이라이트 3~5건
    • 등급 B 이하면 "/humanize-redo로 2차 윤문 가능" 안내

옵션 (인자 끝에 자연어로)

  • 장르: 칼럼|리포트|블로그|공적 — 장르 명시 (생략 시 첫 300자로 자동 추정)
  • 강도: 보수|기본|적극 — 윤문 강도 (기본값: 기본)
  • 최소심각도: S1|S2|S3 — 탐지 임계값 (기본값: S2)
  • --strict — 정밀 3콜(진단→겨냥 윤문→finalize) 강제

참고

  • 분류 체계: humanize-korean/references/ai-tell-taxonomy.md
  • 윤문 처방: humanize-korean/references/rewriting-playbook.md
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. 11d ago First seen · 36 lines · 73 tokens per session scan A 098277d12814

Subscribe to this mod's changes

humanize is a skill published in the GitHub repository epoko77-ai/im-not-ai (5,418 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 537 once invoked, about $0.0004 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.