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 skills/tobyilee/course-builder/curriculum-designnpx skills add tobyilee/course-builder --skill curriculum-designgit 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/curriculum-design)<a href="https://agentmods.dev/skills/tobyilee/course-builder/curriculum-design"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/curriculum-design.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 | $0.00051 | $0.01116 |
| Opus 5 | $0.00026 | $0.00558 |
| Sonnet 5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
curriculum-design 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curriculum Design
ADDIE Analyze+Design 단계를 수행하는 스킬. 주제 분석 → 학습자 분석 → LO 작성 → 섹션/class 분할의 4단계를 책임진다.
왜 이 규칙들이 있는가
LO가 모호하면 slide/note/transcript/quiz 네 저자가 서로 다른 강의를 만든다. LO는 공유 진실이므로 측정 가능해야 하고, Bloom 레벨로 태깅되어야 하며, 한 번 발행되면 재번호 되지 않아야 한다.
Bloom's Taxonomy (revised 2001)
6레벨, 각 레벨에 권장 동사:
| 레벨 | 의미 | 권장 동사 (ko) | 권장 동사 (en) |
|---|---|---|---|
| Remember | 사실·용어 회상 | 나열한다, 정의한다 | list, define, name |
| Understand | 의미 설명·요약 | 설명한다, 요약한다 | explain, summarize, describe |
| Apply | 새 상황에 사용 | 적용한다, 구현한다 | apply, implement, use |
| Analyze | 구성요소 식별·관계 분석 | 분석한다, 비교한다 | analyze, compare, differentiate |
| Evaluate | 판단·논증 | 평가한다, 정당화한다 | evaluate, justify, critique |
| Create | 새로운 산출물 설계 | 설계한다, 합성한다 | design, synthesize, compose |
금지 동사: "안다", "이해한다", "배운다" (측정 불가, 모호). 대신 해당 인지 활동의 구체 행동 동사 사용.
LO 작성 템플릿
LO-<section_num>.<index>: <학습자는> <Bloom 동사> <대상> <조건/기준>
예:
LO-1.2: 학습자는 RSC 페이로드의 직렬화 순서를 설명할 수 있다 (Understand)LO-2.1: 학습자는 서버 컴포넌트와 클라이언트 컴포넌트를 비교하여 적절한 선택 기준을 제시할 수 있다 (Analyze)
Bloom 분포 규칙
- Course 전체: 최소 4개 레벨 커버, Remember+Understand는 합쳐서 ≤40%
- Section 당: 최소 3개 레벨 커버
- Class 당: 1~2개 LO, 보통 동일 Bloom 레벨 또는 인접 레벨
섹션 분할 휴리스틱
개수
section_count = round(target_duration_min / 25)- 최소 2, 최대 8 (너무 많으면 학습 피로)
순서
- 의존성 위상 정렬
- 동일 depth에서는 Remember → Understand → Apply 순 (Bloom 기반 스캐폴딩)
단일 주제 원칙
"React 기초"는 OK, "React + Redux + Testing"은 NO — 이런 경우 섹션 3개로 분리.
Class 분할 휴리스틱
개수
classes_per_section = round(section_duration / 12)(10~15분 기준)- 보통 2~4개
Class 경계 결정 기준
- 개념적 경계 (하나의 개념이 끝나는 지점)
- 실습 전환 (이론 → 예제 사이)
- 인지 부하 한계 (한 class = 한 번의 "아하")
대상 학습자별 튜닝
| audience | LO 비중 | 전제조건 | 용어 |
|---|---|---|---|
| beginner | Remember/Understand 60% | 최소화 | 용어마다 정의 |
| intermediate | Apply/Analyze 60% | 명시만 | 도메인 용어 자유 |
| advanced | Analyze/Evaluate/Create 70% | 상세 | 최신 논문/이슈 참조 |
체크리스트 (완료 전 자가검사)
- 모든 LO가 Bloom 동사로 시작하는가
- Bloom 레벨 분포가 Course ≥4, 각 Section ≥3인가
- LO id가
LO-<sec>.<idx>포맷을 따르는가 - 각 섹션의 모든 LO가 class에 할당되었는가 (orphan LO 없음)
- 각 class가 1~2 LO만 가지고 있는가
- 섹션 개수와 총 duration이 target에 ±15% 이내인가
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 · 89 lines · 51 tokens per session scan A 19e68a31e275
curriculum-design is a skill published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,116 once invoked, about $0.0003 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.