Borrowing it
Nothing to install: this file belongs to tobyilee/course-builder. 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/tobyilee/course-builder/main/.claude/skills/class-planning/SKILL.mdgit clone --depth 1 https://github.com/tobyilee/course-builderWrote 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/skills/tobyilee/course-builder/class-planning)<a href="https://agentmods.dev/skills/tobyilee/course-builder/class-planning"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/class-planning/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.
<a href="https://agentmods.dev/skills/tobyilee/course-builder/class-planning"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/class-planning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.01116 |
| Opus 5.5 | $0.00026 | $0.00446 |
| Sonnet 5.5 | $0.00013 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
class-planning 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 2mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Class Planning — Beat Sheet Design
beat sheet는 slide/note/script 3저자의 공유 계획이다. 3명이 같은 내용을 다른 매체로 표현하기 때문에, beat가 모호하면 세 자산이 어긋난다.
5부 구조
| Beat | 목적 | 비중 (12분 class 기준) |
|---|---|---|
| hook | 학습자 주의 포착, 왜 중요한지 | 45~90s |
| teach | 핵심 개념 전달, 2~3 서브토픽 | 4~6min |
| example | 구체 코드/사례로 추상을 구체화 | 2~4min |
| practice | 미니 자가학습 (퀴즈와 별개) | 30~90s |
| recap | 핵심 3개 요약 | 30s |
Duration이 8분 이하면 practice는 생략 가능. 15분 초과면 teach를 2~3 beat로 더 쪼갠다.
Beat 작성 필드
{
"id": "b1",
"type": "hook" | "teach" | "example" | "practice" | "recap",
"duration_sec": 45,
"key_points": ["핵심1","핵심2","핵심3"],
"lo_ids": ["LO-1.1"],
"examples": [{"lang":"js","snippet":"...","why":"..."}],
"visual_hint": "대조 다이어그램" | "code highlight" | "flowchart" | null,
"speaker_affect": "호기심" | "단호" | "친근" | "엄숙"
}
key_points 작성 원칙
- 문장이 아니라 요점 (5~12 단어)
- 각 key_point는 slide 1 bullet 또는 note 1 단락 또는 script 30~60s에 대응
- 추상 개념만 나열하지 말고 1개 이상 구체 예시를 포함
Beat type별 가이드
hook
- 학습자가 "이거 몰랐네" 느낄 문제 제시
- 정답 노출 금지 (teach에서 해소)
- 나쁜 예: "오늘은 RSC를 배우겠습니다"
- 좋은 예: "이 페이지 로드가 왜 3초나 걸릴까요? 범인은 의외로..."
teach
- 개념 정의 → 속성 2~3개 → 왜 중요 (3단 구조)
- 서브토픽이 3개 이상이면 beat 분할
example
- 실행 가능한 코드 또는 현실 사례
- "왜 이 예시냐"를
why필드에 명시 (저자들이 설명 재현할 때 참조)
practice
- 사지선다가 아니라 open question
- 답은 제공하지 않음 (다음 beat에서 간접적으로 제시)
recap
- 정확히 3개 핵심 bullet
- 다음 class의 teaser가 있으면 가산점
visual_hint (slide-author 힌트)
- 추상 개념 → "비교 표" or "대조 다이어그램"
- 프로세스 → "flowchart"
- 코드 → "code highlight with arrow"
- 수치·비율 → "bar chart"
speaker_affect (script-writer 힌트)
class의 tone 파라미터 위에서 beat별 세부 조정:
- hook:
호기심,약간 미스터리 - teach:
차분,명료 - example:
흥분 섞인 설명 - practice:
질문하는 톤, 침묵 허용 - recap:
힘 실린 확신
Duration 검증
sum(beats.duration_sec) ∈ [target_sec × 0.9, target_sec × 1.1]
초과 시: 가장 긴 teach/example부터 압축. 부족 시: teach 확장.
LO 매핑 규칙
- 모든 beat는 ≥1 LO 참조
- LO 없는 beat는 잡담이므로 삭제
- recap은 class의 모든 LO를 커버해야 함
재실행 규칙
- beat id 재번호 금지
- 구조 유지한 채 key_points만 교체 가능
- duration 변경은 이웃 beat까지 재배분 필요 (class 총합 불변)
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.
- 2mo ago First seen · 103 lines · 64 tokens per session scan A aab601946f85
class-planning is a skill published in the GitHub repository tobyilee/course-builder (27 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 1,116 once invoked, about $0.0003 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 2026-08-30.
class-planning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| class-planningtobyilee/course-builder | Skill | 27 | 6mo ago | MIT | A | 64 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |
| eli5companion-inc/feynman | Skill | 10k | 7d ago | MIT | A | 63 | Claude Code, Codex |