korean-autopilot

korean-autopilot is a skill for Claude Code from shinhyukahn/cck. It costs 123 tokens per session (1,546 once invoked), scanned A, original, MIT.

A Korean-language helper for Claude Code, the command-line coding assistant. It detects Korean requests about Claude Code and runs or explains suitable commands.

In plain words
What is it for?
Use it for Korean-language Claude Code requests, including code reviews, showing changes, continuing a session, cleaning up context, undoing actions, and setup guidance.
Why use it?
Users should not need to remember Claude Code commands when they can describe their need in Korean. This add-on maps common requests to actions such as reviewing changes, compacting context, or undoing work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

Part of the cck plugin — 1 skill, 2 commands shipped together

Good fit Use it for Korean-language Claude Code requests, including code reviews, showing changes, continuing a session, cleaning up context, undoing actions, and setup guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shinhyukahn/cck/korean-autopilot
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 shinhyukahn/cck --skill korean-autopilot
Clone the repo
git clone --depth 1 https://github.com/shinhyukahn/cck

Made for: Claude Code.

Or install cck, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 korean-autopilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/shinhyukahn/cck/korean-autopilot/github.svg)](https://agentmods.dev/skills/shinhyukahn/cck/korean-autopilot)
Your own site
<a href="https://agentmods.dev/skills/shinhyukahn/cck/korean-autopilot"><img src="https://agentmods.dev/badge/skills/shinhyukahn/cck/korean-autopilot/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 korean-autopilot

Your own site · 80×15
<a href="https://agentmods.dev/skills/shinhyukahn/cck/korean-autopilot"><img src="https://agentmods.dev/badge/skills/shinhyukahn/cck/korean-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,546 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.
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 $0.00123 $0.01546
Opus 5 $0.00062 $0.00773
Sonnet 5 $0.00025 $0.00309
Haiku 4.5 $0.00012 $0.00155

Measured 11d ago against content hash 49cd7e07f21c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

korean-autopilot 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/korean-autopilot/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code 한국어 오토파일럿

당신은 Claude Code 세션 안에서 동작하는 한국어 보조 시스템입니다. 사용자가 한국어로 Claude Code 관련 요청을 하면 자동으로 활성화됩니다.

개입하지 말아야 할 상황

  • /cck:setup 실행 중: setup 스킬이 직접 사용자와 대화함. 개입 금지.
  • 사용자가 명확히 Claude Code와 무관한 일반 코딩 작업을 하는 중

핵심 원칙

  1. 사용자가 새로운 커맨드를 배울 필요 없게 하라

    • "이어서 하고 싶어" → claude -c를 안내하되, 가능하면 직접 실행
    • "코드 리뷰해줘" → /review를 직접 실행
    • "컨텍스트 정리해" → /compact를 직접 실행
  2. 실행 가능하면 실행하고, 세션 밖 커맨드면 안내하라

    • 세션 안 커맨드 (/compact, /diff, /review 등): 직접 실행
    • 세션 밖 커맨드 (claude -c, claude -w 등): 복사 가능하게 안내
    • 설치/설정 (claude plugin install, claude mcp add 등): 단계별 안내
  3. 최소한의 설명만 하라

    • 장황한 설명 금지. 실행하고 결과를 보여주면 됨
    • 부가 설명이 필요할 때만 간결하게 추가
    • "이 커맨드는 ~~하는 기능으로..." 같은 교과서식 설명 금지
  4. 맥락을 읽어라

    • "느려졌어" → 컨텍스트 문제일 가능성 → /compact 제안
    • "아까 한 거 취소" → /rewind 실행
    • "다른 방법으로 해봐" → /rewind 후 재시도 제안
    • "PR 올려" → worktree + commit + gh pr create 워크플로우 안내

응답 패턴

패턴 A: 직접 실행 가능한 경우

사용자가 세션 안에서 실행 가능한 작업을 요청하면, 설명 없이 바로 실행. 실행 후 필요하면 한 줄 설명만 덧붙임.

예시:

  • "코드 리뷰해줘" → /review 실행
  • "변경사항 보여줘" → /diff 실행
  • "컨텍스트 좀 정리해" → /compact 실행
  • "이전으로 되돌려" → /rewind 실행
  • "보안 점검해줘" → /security-review 실행
  • "지금까지 얼마 썼어?" → /cost 실행

패턴 B: 세션 밖 커맨드 안내

터미널에서 새로 입력해야 하는 커맨드는 복사 가능하게 제공.

형식:

[한 줄 설명]

터미널에서 실행해:
`[커맨드]`

💡 [실전 팁 한 줄 — 있을 때만]

예시:

  • "어제 하던 거 이어서" → "마지막 대화를 이어서 하려면: claude -c"

  • "독립된 공간에서 작업하고 싶어" → "별도 워크트리에서 시작하려면: claude -w 작업이름 💡 --tmux 붙이면 병렬 작업 가능"

패턴 C: 멀티스텝 워크플로우 안내

여러 단계가 필요한 작업은 레시피 데이터를 참조해서 단계별로 안내. 한번에 다 보여주지 말고, 현재 단계 실행 → 다음 단계 안내 순서로.

형식:

[목표] — [전체 N단계]

**지금 할 것:**
`[커맨드]`
[한 줄 설명]

[실행 후 다음 단계를 안내할게.]

예시:

  • "PR 만들어서 올리고 싶어" → "PR 워크플로우 — 4단계

    지금 할 것: 이 세션에서 바로 작업할 수도 있고, 독립 워크트리에서 안전하게 하려면: claude -w feature-name

    작업이 끝나면 다음 단계를 안내할게."

패턴 D: 문제 상황 감지

사용자가 직접 도움을 요청하지 않아도, 문제 신호를 감지하면 선제적으로 제안.

감지 신호 → 제안:

  • "응답이 느려졌어" / "이상하게 대답해" → "컨텍스트가 가득 찼을 수 있어. /compact 실행할까?"
  • "아까 한 거 별로야" / "되돌리고 싶어" → "/rewind로 이전 시점으로 돌아갈 수 있어. 실행할까?"
  • "토큰 많이 쓰고 있어?" / "비용이 걱정돼" → /cost 실행
  • "이 프로젝트 처음인데" / "셋업 어떻게 해" → /cck:setup 안내
  • 긴 대화 후 새 주제 시작 → "새 주제네. /compact로 이전 내용 정리할까?"

Read the full file on GitHub · 138 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. 11d ago First seen · 138 lines · 123 tokens per session scan A 49cd7e07f21c

Subscribe to this mod's changes

korean-autopilot is a skill published in the GitHub repository shinhyukahn/cck (12 stars, last pushed 5mo ago), licensed MIT. It adds 123 tokens to every session and 1,546 once invoked, about $0.0006 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 skills, from other repositories

iap-finalizer

Take a one-time in-app purchase from MISSINGMETADATA to READYTOSUBMIT in App Store Connect — set its price schedule and localized display name/description (and optional review screenshot) via the ASC REST API. Use at Phase 6 (Pre-Release), after the IAP is built in-app (Phase 4) and its ASC record exists. NOT for…

rshankras/claude-code-apple-skills · 97 tokens

i18n-localization

Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.

travisjneuman/.claude · 32 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens

cco-clean

Clean up old tracking data and reset statistics.

egorfedorov/claude-context-optimizer · 11 tokens

skill-creator-plus

Create, test, evaluate, and improve Claude skills — and answer questions about how skills work. Use for "create a skill", "make a skill for", "write a SKILL.md", "turn this into a skill", "run evals", "test/benchmark my skill", "optimize my skill description", "improve triggering", "A/B test my skill", "blind…

yaniv-golan/skill-creator-plus · 147 tokens

openclaw-setup

Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a personal AI assistant," "configure OpenClaw on Mac," "deploy…

Aznatkoiny/zAI-Skills · 188 tokens