agentmods.dev

humanizer-ko: Instructions file for Claude Code

AGENTS.md

humanizer-ko AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from IsaacEryn/humanizer-ko. It costs 924 tokens per session, scanned A, original, MIT.

A set of instructions for maintaining the humanizer-ko project, a Korean-language text-editing skill for coding agents. It explains the project's files, editing rules, versioning, and validation checks.

In plain words
What is it for?
Use it when editing, reviewing, validating, or releasing the humanizer-ko skill and its Korean text patterns.
Why use it?
It helps contributors change the skill without breaking the required files, pattern numbering, version references, or consistency between the source and README.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions Claude Code; mentions AGENTS.md.

This is IsaacEryn/humanizer-ko's own configuration. It tells Claude Code, Codex and OpenCode how to work on humanizer-ko 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 humanizer-ko configures →

not rated 6repo changed 7d ago A scan 924 tokens original MIT
View source ↗ IsaacEryn/humanizer-ko
Reuse

Borrowing it

Nothing to install: this file belongs to IsaacEryn/humanizer-ko. 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/IsaacEryn/humanizer-ko/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/IsaacEryn/humanizer-ko

Made for: Claude Code, Codex, OpenCode.

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 humanizer-ko AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isaaceryn/humanizer-ko/agents-md/github.svg)](https://agentmods.dev/instructions/isaaceryn/humanizer-ko/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/isaaceryn/humanizer-ko/agents-md"><img src="https://agentmods.dev/badge/instructions/isaaceryn/humanizer-ko/agents-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 humanizer-ko AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/isaaceryn/humanizer-ko/agents-md"><img src="https://agentmods.dev/badge/instructions/isaaceryn/humanizer-ko/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 924 This file is loaded in full into every session.
When invoked 924 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 $0.00924 $0.00924
Opus 5.5 $0.00370 $0.00370
Sonnet 5.5 $0.00185 $0.00185
Haiku 4.5 $0.00092 $0.00092

Measured 7d ago against content hash 659779934f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

humanizer-ko AGENTS.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 7d 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.

AGENTS.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

이 저장소에서 작업하는 AI 코딩 에이전트(Claude Code, Codex, Warp 등)를 위한 안내.

이 저장소는 무엇인가

전부 Markdown으로 구현된 이식 가능한 에이전트 스킬이다. 런타임 산출물은 SKILL.md 하나다: 에이전트가 YAML frontmatter와 편집자 프롬프트를 읽는다. 빌드 단계는 없으며, 특정 하네스 한두 개에만 묶이는 표현은 피한다.

blader/humanizer의 포크이며, 패턴 전체를 한국어 텍스트 전용으로 재설계했다. upstream의 패턴 추가·수정은 그대로 병합하지 말고, 한국어에 유효한지 판단해 선별 번안한다.

주요 파일

  • SKILL.md — 스킬 본체. 500줄 예산이 차 있어 긴 보조 절은 references/로 뺀다(지금은 발표 대본용 references/spoken-scripts.md와 학술 원고용 references/academic-papers.md). 이식 가능한 YAML frontmatter(name, description, license, metadata.version)와 번호 붙은 패턴 목록(Before/After 예시 포함). 이 파일이 진실의 원천이다.
  • README.md — 사람용: 설치, 사용법, 패턴 요약 표, 버전 이력. 한국어 우선, 영어 요약 병행.
  • .claude-plugin/plugin.json — 선택적 Claude Code 플러그인 매니페스트.
  • .claude-plugin/marketplace.json — /plugin marketplace add IsaacEryn/humanizer-ko가 동작하게 하는 단일 저장소 마켓플레이스 항목.
  • scripts/validate-package.py — 로컬과 CI에서 쓰는 의존성 없는 패키지·동기화 검사.

유지보수 계약

SKILL.md와 README.md는 동기화를 유지해야 한다. 동작이나 내용을 바꿀 때:

  • 패턴: 스킬은 현재 37개 번호 패턴을 정의한다. 추가·삭제·번호 변경 시 README 패턴 표와 「37개 탐지 패턴」 제목, 본문의 모든 상호 참조(§N)를 같은 변경에서 함께 고친다. 의도적인 재번호가 아니면 번호를 유지한다. 검증 스크립트가 패턴 번호를 순서까지 비교하므로 새 패턴은 마지막 번호 뒤에 붙인다.
  • 버전: SKILL.md frontmatter의 metadata.version, README.md의 「버전 이력」, .claude-plugin/plugin.json의 version 세 곳을 함께 올린다. 스킬 버전은 metadata 아래에 둔다. 최상위 version 키는 Agent Skills 호스트 간 이식성이 없다. (marketplace.json은 의도적으로 버전을 생략해 plugin.json이 패키지의 단일 출처가 되게 한다.)
  • 호환성: 설치·사용 문구를 하네스 중립으로 유지한다. Markdown 스킬 지침을 읽을 수 있는 어떤 하네스에서도 동작해야 하며, Claude Code·OpenCode·Codex 등은 예시이지 한계가 아니다.
  • 검증: 게시 전에 python3 scripts/validate-package.py, npx skills add . --list, claude plugin validate .를 실행한다.
  • 까다로운 수정: 특정 실패 양상(반복되는 오교정, 예상 밖의 톤 변화)을 잡으려고 프롬프트를 고쳤다면, 무엇을 왜 고쳤는지 README 버전 이력에 짧게 남긴다.

SKILL.md 편집

  • 유효한 YAML frontmatter(형식과 들여쓰기)를 보존한다.
  • frontmatter 아래 프롬프트가 곧 제품이다. 코드가 아니라 신중한 지침 문서로 다룬다.
  • 예시는 전부 한국어를 유지한다. 감시 표현은 실제 한국어 LLM 출력에서 관찰되는 것이어야 하며, 영어 티의 직역이어서는 안 된다.

Read the full file on GitHub · 34 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. 7d ago Changed · +18 tokens per session 659779934f64
  2. 9d ago Changed · +34 tokens per session f11e4f3c8f6c
  3. 1mo ago First seen · 34 lines · 872 tokens per session scan A dfa51092ba8f

Subscribe to this mod's changes

humanizer-ko AGENTS.md is an instructions file published in the GitHub repository IsaacEryn/humanizer-ko (6 stars, last pushed 8d ago), licensed MIT. It adds 924 tokens to every session, about $0.0037 per session on Opus 5.5. 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 2026-08-31.

Claude Codeagent-skillsai-detectionai-writingclaude-skillediting
Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens