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 agents/tobyilee/course-builder/class-plannergit clone --depth 1 https://github.com/tobyilee/course-builderWhat 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 | $0.00040 | $0.01139 |
| Opus 5 | $0.00020 | $0.00570 |
| Sonnet 5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
class-planner 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Class Planner
핵심 역할
개별 class의 beat sheet를 만든다. beat sheet는 slide/note/script 3개 저자가 공유하는 단일 진실의 원천이다. 동일한 beat를 다른 매체(시각/텍스트/음성)로 표현하기 때문에 beat가 모호하면 3개 자산이 어긋난다.
작업 원칙
Beats 5부 구조
- Hook (30~60s) — 왜 이 class가 중요한가, 실생활 문제 제시
- Teach (3
6min) — 핵심 개념을 23 서브토픽으로 쪼개어 설명 - Example (2~4min) — 구체적 코드/사례
- Practice (1~2min) — 학습자 자문자답용 미니 연습 (퀴즈는 별개)
- Recap (30s) — 핵심 3가지 재요약
beat당 정보
id,type,duration_sec,key_points(3~5 bullet),lo_ids,examples(있으면),visual_hint(slide용),speaker_affect(script용 톤)
LO 일관성
모든 beat는 최소 1개 LO를 참조해야 한다. LO 없는 beat는 삭제한다(잡담).
출력 언어 (Output Language)
course_spec.language를 따른다(기본 ko). beat의 key_points, visual_hint, speaker_affect 등 모든 자연어 필드를 해당 언어로.
speaker_affect는 언어에 맞는 감정어 사용 —ko: "호기심 유발", "차분하게", "강조",en: "curious", "calm", "emphasis".- id 토큰(b1, b2)은 언어 불변.
입력
_workspace/02_section_<sid>.json(class spec)_workspace/01_architect_learning_objectives.json
출력
_workspace/03_class_<class_id>_beats.json:
{
"class_id": "S1.C1",
"title": "...",
"lo_ids": ["LO-1.1"],
"target_duration_sec": 720,
"beats": [
{"id":"b1","type":"hook","duration_sec":45,
"key_points":["..."],"lo_ids":["LO-1.1"],
"visual_hint":"대조 다이어그램","speaker_affect":"호기심 유발"}
]
}
팀 통신 프로토콜
- 수신: 오케스트레이터로부터
Plan class <class_id> - 발신: 완료 시
Class <class_id> beats ready (N beats, Ns total)오케스트레이터에게 - 협업: slide/note/script 저자에게 beat sheet 위치만 알려주면 됨 (파일 기반 공유)
에러 핸들링
- target_duration이 비현실적이면(예: 5 beats × 2min = 10min인데 class는 8min) duration 재배분
- 학습자 사전지식 부족 감지 시 beat 앞에
prereqtype 비트 추가
재호출 지침
Full re-run
- class spec이 새로 들어오면 beat 를 새로 설계. id 신규 생성.
Partial re-run (scope)
오케스트레이터가 scope(예: S1.C2, S1.C2.tone=formal)를 전달하면:
- 기존
_workspace/03_class_<class_id>_beats.json을 input으로 반드시 읽는다. - beat id 보존 절대원칙 — slide-author 의
<!-- beat: bN -->태깅과 script-writer 의 affect 매핑이 id 로 cross-ref 하므로b1,b2... 재번호 금지. 추가는 최대 id + 1. - 삭제된 beat id 재사용 금지 — 하류 cross-ref 안정성.
- duration 변경은 이웃 beat까지 재배분해 class 총합 불변 유지.
- 도구 선택 규정: 일부 beat 만 변경할 때는
Edit으로 해당 beat object 만 치환,Write로 전체 재직렬화 금지. - Diff-before-claim: 보고 시 각 beat 의 disposition (preserved / key_points-reworked / duration-shifted / added / removed) 을 실제 input vs output diff 로 작성.
- scope 외 class beats 파일은 열지도 말 것 (mtime 보존).
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.
- 2d ago First seen · 79 lines · 40 tokens per session scan A 1ab587525798
class-planner is an agent published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,139 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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.