Borrowing it
Nothing to install: this file belongs to shinhyukahn/cck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shinhyukahn/cck/main/CLAUDE.mdgit clone --depth 1 https://github.com/shinhyukahn/cckWrote 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/instructions/shinhyukahn/cck/claude-md)<a href="https://agentmods.dev/instructions/shinhyukahn/cck/claude-md"><img src="https://agentmods.dev/badge/instructions/shinhyukahn/cck/claude-md.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 | $0.00933 | $0.00933 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
cck CLAUDE.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 6d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
프로젝트 개요
CCK(Claude Code Korean)는 한국어 사용자가 Claude Code를 자연어로 사용할 수 있게 해주는 투명한 플러그인이다. 구현 완료 상태이며, 지속적으로 커맨드 DB와 레시피를 확장하는 것이 목표다.
- 설계 원칙: 투명성 (사용자가 CCK 존재를 몰라도 됨), 명시적 호출 최소화
- 핵심 동작:
korean-autopilot스킬이 한국어를 감지해서 자동 라우팅
디렉토리 구조
cck/
├── .claude-plugin/
│ └── plugin.json # 플러그인 매니페스트
├── data/
│ ├── commands.json # 커맨드 DB (한국어 메타데이터 포함)
│ ├── aliases.json # 한국어 자연어 → 커맨드 ID 매핑
│ └── recipes.json # 멀티스텝 워크플로우 레시피
├── skills/
│ ├── korean-autopilot/ # 백그라운드 자동 활성화 스킬 (user-invocable: false)
│ │ └── SKILL.md
│ ├── cheat/ # 사용자 호출: /cck:cheat
│ │ └── SKILL.md
│ └── setup/ # 사용자 호출: /cck:setup [프로젝트유형]
│ ├── SKILL.md
│ └── templates/
│ ├── web-app.md
│ ├── api-server.md
│ ├── data-pipeline.md
│ ├── monorepo.md
│ └── side-project.md
├── agents/
│ └── korean-helper.md # 한국어 도움 서브에이전트
└── README.md
핵심 설계 원칙
- 투명성: 사용자가 CCK의 존재를 몰라도 됨. 한국어로 말하면 Claude가 알아서 처리
- 사용자 호출 스킬 최소화: 명시적 호출은
/cck:cheat,/cck:setup2개만 - korean-autopilot이 나머지 모든 기능을 흡수 (찾기 + 레시피 + 설명)
- 실행 가능/불가 구분:
session_executable: true면 직접 실행,false면 터미널 커맨드로 안내
데이터 스키마
commands.json 핵심 필드
session_executable: 세션 내에서 직접 실행 가능한지 여부 (true = 패턴 A 직접실행, false = 패턴 B 터미널안내)tags: 한국어 자연어 검색 키워드summary_ko/detail_ko: 한국어 설명
aliases.json
자연어 키워드 → 커맨드 ID 배열. 예: "이어서": ["continue-flag", "resume"]
recipes.json
step 타입: "terminal" (복사 가능 안내), "claude-command" (직접 실행), "claude-prompt" (사용자 프롬프트)
korean-autopilot 응답 패턴
- 패턴 A (session_executable: true): 설명 없이 바로 실행
- 패턴 B (session_executable: false): 터미널에서 실행할 커맨드를 복사 가능한 코드 블록으로 안내
- 패턴 C (멀티스텝): recipes.json 참조, 현재 단계 실행 후 다음 단계 안내
- 패턴 D (문제 감지): 사용자가 요청 안 해도 선제적으로 제안 (예: 느려졌을 때
/compact)
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.
- 6d ago First seen · 72 lines · 933 tokens per session scan A de0e9d935021
cck CLAUDE.md is an instructions file published in the GitHub repository shinhyukahn/cck (12 stars, last pushed 5mo ago), licensed MIT. It adds 933 tokens to every session, about $0.0047 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 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.
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.
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).
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).
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.
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.