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.
npx agentmods add commands/ww-w-ai/bkit-starter/learn-claude-codegit clone --depth 1 https://github.com/ww-w-ai/bkit-starterWrote 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/commands/ww-w-ai/bkit-starter/learn-claude-code)<a href="https://agentmods.dev/commands/ww-w-ai/bkit-starter/learn-claude-code"><img src="https://agentmods.dev/badge/commands/ww-w-ai/bkit-starter/learn-claude-code.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 | $0.00017 | $0.01420 |
| Opus 5 | $0.00009 | $0.00710 |
| Sonnet 5 | $0.00003 | $0.00284 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
learn-claude-code 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 4d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 학습 가이드
사용자에게 Claude Code 설정 방법을 교육합니다. 어떤 프로젝트, 어떤 언어에서든 동일하게 작동합니다.
사용법
/learn-claude-code [레벨]
- 레벨 생략 시: 현재 설정 분석 후 적합한 레벨 추천
- 레벨 지정: 1 (기초), 2 (자동화), 3 (전문화), 4 (팀 최적화)
왜 이 커맨드가 필요한가?
문제: Claude Code 기능이 많아서 어디서부터 배워야 할지 모름
해결: 현재 설정 수준을 분석하고 레벨별 교육 콘텐츠 제공
결과: 단계별로 Claude Code 마스터
수행 작업
1단계: 마스터 가이드 참조
반드시 다음 문서를 먼저 읽어야 합니다:
.claude/docs/CLAUDE-CODE-MASTERY.md # 목차 및 핵심 개념
.claude/docs/mastery/04-curriculum.md # 교육 커리큘럼 (레벨 시스템 정의)
.claude/docs/mastery/02-language-templates.md # 언어별 템플릿
.claude/docs/mastery/03-project-structures.md # 프로젝트 구조별 가이드
2단계: 현재 설정 분석
프로젝트의 Claude Code 설정 현황을 분석합니다:
# 분석할 파일/폴더
- CLAUDE.md (루트)
- .claude/settings.local.json
- .claude/commands/
- .claude/agents/
- .claude/skills/
- .mcp.json
- .github/workflows/
기본 제공 파일 제외 (중요!)
다음 파일/폴더는 이 학습 시스템의 기본 제공 파일이므로 평가 시 제외해야 합니다:
# 제외할 파일/폴더 (사용자 설정으로 카운트하지 않음)
- .claude/commands/learn-claude-code.md # 학습 커맨드
- .claude/commands/setup-claude-code.md # 설정 생성 커맨드
- .claude/commands/upgrade-claude-code.md # 업그레이드 커맨드
- .claude/commands/first-claude-code.md # 첫 프로젝트 커맨드
- .claude/docs/ # 마스터 가이드 문서 전체
3단계: 레벨 및 체크리스트 평가
중요: 레벨 정의, 항목별 체크리스트, 대시보드 형식은 모두 .claude/docs/mastery/04-curriculum.md의 "4.0 Claude Code 설정 현황 시스템"을 참조합니다.
해당 문서에서 다음 내용을 확인:
- 레벨 정의 (0-5)
- 항목별 체크리스트 (8개 항목)
- 대시보드 출력 형식
- 빠른 레벨업 가이드
4단계: 대시보드 출력
.claude/docs/mastery/04-curriculum.md의 "대시보드 출력 형식"에 따라 분석 결과를 시각화합니다.
5단계: 교육 콘텐츠 제공
현재 레벨에 맞는 교육 콘텐츠를 .claude/docs/mastery/04-curriculum.md에서 참조:
| 레벨 | 참조 섹션 | 핵심 안내 |
|---|---|---|
| 0 | 4.0 설정 현황 시스템 | /first-claude-code 또는 /setup-claude-code 안내 |
| 1 | 4.1 레벨 1: 기초 | CLAUDE.md 작성법, 금지사항 추가 |
| 2 | 4.2 레벨 2: 자동화 | Commands 생성, Hooks 설정 |
| 3 | 4.3 레벨 3: 전문화 | Agents, Skills, MCP 연결 |
| 4 | 4.4 레벨 4: 팀 최적화 | GitHub Action, 팀 규칙 |
동적 개선 제안:
현재 상태를 기반으로 가장 효과적인 개선 방법을 제안합니다:
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.
- 4d ago First seen · 162 lines · 17 tokens per session scan A 6636d2095490
learn-claude-code is a command published in the GitHub repository ww-w-ai/bkit-starter (53 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 1,420 once invoked, about $0.0001 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 commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
learn
LEARN MODE - Explains concepts with a gentle, Socratic, and human-like coaching persona.
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
debrief
Post-engagement lessons learned analysis and debrief report.