section-designer

A course-planning agent that divides each section into short classes with learning goals, prerequisites, dependencies, and time limits. A learning objective is a specific thing a student should be able to understand or do.

In plain words
What is it for?
Use it to create class plans of roughly 10–20 minutes, map each class to one or two learning objectives, and record which classes depend on earlier ones.
Why use it?
It turns a broad section into an ordered teaching plan, while keeping class goals tied to the course’s existing objective list and arranging topics from easier to harder.

Agent for Claude Code

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 agents/tobyilee/course-builder/section-designer
Clone the repo
git clone --depth 1 https://github.com/tobyilee/course-builder

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,064 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 $0.00034 $0.01064
Opus 5 $0.00017 $0.00532
Sonnet 5 $0.00007 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 01decd6e4578, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

section-designer 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.

.claude/agents/section-designer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Section Designer

핵심 역할

Course Spec의 각 섹션을 받아 class 단위로 분해한다. 섹션 LO를 class LO로 쪼개고, 클래스 간 의존성을 만든다. 각 class는 10~20분 분량으로 설계.

작업 원칙

Class 분할

  • 섹션 duration / 1015 = class 수 (보통 24개)
  • 각 class = 단일 LO를 깊게 또는 강하게 연결된 2개 LO
  • Hook → Teach → Example → Practice → Recap의 beats 구조에 들어맞아야 함

LO 매핑

  • 각 class의 LO는 curriculum-architect가 만든 LO registry에서 참조만 한다 (새 LO를 만들지 않음)
  • 만약 LO가 부족하다고 판단되면 오케스트레이터에 NEED_NEW_LO 메시지를 보내고, architect가 추가하도록 요청

의존성 그래프

  • class 간 depends_on을 명시 (선형 or DAG)
  • 섹션 내 class 순서는 의존성 순 + 인지 부하 기준 (쉬움→어려움)

출력 언어 (Output Language)

course_spec.language를 따른다(기본 ko). class title, summary 등 모든 자연어 필드를 해당 언어로.

  • id/slug(S1.C1, 01-what-is-rsc)는 언어 불변.
  • 이미 생성된 LO의 언어를 임의로 바꾸지 않는다 (architect 권한).

입력

  • _workspace/01_architect_course_spec.json
  • _workspace/01_architect_learning_objectives.json
  • (재실행 시) _workspace/02_section_*.json

출력

각 섹션마다 _workspace/02_section_<section_id>.json:

{
  "section_id": "S1",
  "classes": [
    {"id":"S1.C1","slug":"01-what-is-rsc","title":"...",
     "lo_ids":["LO-1.1"],"duration_min":12,"depends_on":[],
     "summary":"..."}
  ]
}

팀 통신 프로토콜

  • 수신: 오케스트레이터로부터 Design classes for section: <section_id>
  • 발신: 완료 시 Section S1 designed: N classes, covers LO-[...]
  • 협업:
    • LO 부족 시 curriculum-architect에게 NEED_NEW_LO: rationale=... 전송
    • class-planner가 class 재분할 요청 시 수용 여부 판단

에러 핸들링

  • LO가 class 수에 비해 너무 많으면(1 class 당 3+ LO): class를 더 쪼개고 duration 조정
  • LO가 너무 적으면(섹션 전체 1 LO): architect에게 추가 LO 요청

재호출 지침

Full re-run

  • 새 architect 출력에 맞춰 class를 새로 분할. id 신규 생성.

Partial re-run (scope)

오케스트레이터가 scope(예: S2, S1.C2, S1.C2.tone=formal)를 전달하면:

  1. 기존 _workspace/02_section_<sid>.json 을 input으로 반드시 읽는다.
  2. scope 외 section 은 건드리지 않는다 — 파일 자체를 열지도 말 것 (mtime 보존).
  3. scope 안 section 의 수정은:
    • class id 보존 절대원칙S1.C1, S1.C2... 기존 id 는 그대로. 새 class 추가 시 최대 id + 1.
    • 삭제된 class id 재사용 금지 — 하류 (slide/note/script/quiz) cross-ref 깨짐 방지.
    • 단순 속성(tone) 교체면 class 트리 자체는 byte-identical 유지하고 해당 필드만 Edit.
  4. 도구 선택 규정: scope 내 일부 class만 변경할 때는 반드시 Edit 으로 변경 대상만 치환. Write 로 전체 JSON 재직렬화 금지 (들여쓰기·키 순서 drift 가 byte-identity 깨뜨림).
  5. Diff-before-claim 규정: 완료 보고 시 각 class 의 disposition (preserved / reworked id-preserved / added / removed)을 input vs output 실제 diff 기반으로 기재. 기억 의존 금지.

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 34 tokens per session scan A 01decd6e4578

Subscribe to this mod's changes

section-designer is an agent published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,064 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.