cheat

A Korean-language quick reference for Claude Code commands, options, and common project actions. Claude Code is a command-line coding assistant.

In plain words
What is it for?
Use it to look up commands for starting sessions, managing context and permissions, reviewing code, handling pull-request comments, and running work in separate workspaces.
Why use it?
It reduces the need to remember command names and flags when using Claude Code.

Command

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.

agentmods
npx agentmods add commands/shinhyukahn/cck/cheat
Clone the repo
git clone --depth 1 https://github.com/shinhyukahn/cck
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00698
Opus 5 $0.00023 $0.00349
Sonnet 5 $0.00009 $0.00140
Haiku 4.5 $0.00005 $0.00070

Measured 2d ago against content hash f1fb20b157a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cheat 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 2d 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.

commands/cheat.md · 77 lines

What it actually says

아래 내용을 그대로 출력해. 한 글자도 바꾸지 말고, 앞뒤에 아무것도 붙이지 마.


⚡ Claude Code 치트시트

시작하기

커맨드 설명
claude 대화 시작
claude "질문" 질문과 함께 시작
claude -c 마지막 대화 이어서
claude -r <이름> 특정 세션 복구
claude -n "이름" 세션에 이름 붙이기
cat file | claude -p "질문" 파일 내용 넘겨서 질문

대화 중 자주 쓰는 것

커맨드 설명
/compact 컨텍스트 정리 (요약)
/clear 대화 완전 초기화
/model 모델 변경
/diff 변경사항 보기
/rewind 이전 시점으로 되돌리기
/cost 토큰 사용량 확인
/copy 마지막 응답 복사
/context 컨텍스트 사용량 시각화

프로젝트 관리

커맨드 설명
/init CLAUDE.md 생성
/memory 메모리 파일 관리
/permissions 권한 규칙 관리
/plugin 플러그인 관리
/skills 사용 가능한 스킬 목록

코드 작업

커맨드 설명
/review 코드 리뷰 (플러그인 필요)
/security-review 보안 취약점 분석
/simplify 코드 품질 개선
/batch <지시> 대규모 변경 병렬 처리
/pr-comments PR 코멘트 확인

실행 옵션 (플래그)

플래그 설명
--worktree (-w) 독립 작업 공간에서 실행
--effort high 더 깊이 생각하게
--model sonnet 모델 지정
--tmux tmux 세션으로 열기
--chrome 브라우저 자동화 활성화
--dangerously-skip-permissions 권한 확인 건너뛰기

단축키

설명
Shift+Tab 권한 모드 전환
Ctrl+C 현재 응답 중단
Ctrl+L 화면 정리
Esc (2번) 현재 작업 중단
Shift+Enter 여러 줄 입력

💡 더 자세한 설명이 필요하면 한국어로 물어보면 돼. 예: "worktree가 뭐야?", "PR 어떻게 올려?"

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. 2d ago First seen · 77 lines · 45 tokens per session scan A f1fb20b157a6

Subscribe to this mod's changes

cheat is a command published in the GitHub repository shinhyukahn/cck (12 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 698 once invoked, about $0.0002 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.