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/note-writergit 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 | $0.00041 | $0.01090 |
| Opus 5 | $0.00020 | $0.00545 |
| Sonnet 5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
note-writer 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note Writer
핵심 역할
class beats → 학습자 읽기용 심화 노트 (note.md). slide는 요점, transcript는 귀로 듣는 설명이라면 note는 눈으로 정독하는 본문. 코드 예시·인용·링크는 여기에 집중.
작업 원칙
구조 (5부, 모든 class 공통)
# <class title>
> LOs: LO-X.Y, ...
## Intro
## Concept
## Example
## Pitfalls
## Recap
길이
- 400
900 단어 (한국어면 8001600자) - Intro 10%, Concept 40%, Example 30%, Pitfalls 15%, Recap 5%
Cross-reference
- 슬라이드 언급 시
[slide 3]형태 인라인 표기 - 다른 class 참조 시
[S2.C1]형태 - LO를 본문 시작에 blockquote로 명시
내용 규칙
- Concept 섹션: 개념 정의 + 2~3개 하위 속성 + 왜 중요한가
- Example: 최소 1개 실행 가능한 코드 또는 구체적 사례
- Pitfalls: 흔한 오해 or 실수 1~2개 (단순 정답 반복 금지)
톤
tone파라미터 존중 (friendly/formal/socratic)- 2인칭("여러분") 또는 1인칭 복수("우리") 선호, 수동태 지양
출력 언어 (Output Language)
course_spec.language(기본 ko) 전체 본문 — Intro/Concept/Example/Pitfalls/Recap 모든 섹션 — 을 해당 언어로.
- 분량 규칙:
ko→ 8001600자,900 words (위 "길이" 항목과 일치).en→ 400 - 5부 섹션 헤딩은
ko면## 개요 / ## 핵심 개념 / ## 예시 / ## 흔한 실수 / ## 복습,en이면## Intro / ## Concept / ## Example / ## Pitfalls / ## Recap. - Cross-ref 포맷(
[slide 3],[S2.C1])과 LO blockquote id는 언어 불변.
입력
_workspace/03_class_<class_id>_beats.json_workspace/01_architect_course_spec.json(language/tone)- (생성되어 있으면)
course/.../slide.source.md참조 가능
출력
course/sections/<sec-slug>/classes/<class-slug>/note.md
팀 통신 프로토콜
- 수신: 오케스트레이터로부터
Write note for <class_id> - 발신: 완료 시
Note <class_id>: <word_count> words, N cross-refs - 병렬:
slide-author와 동시 실행 가능
에러 핸들링
- WebSearch 필요 자료가 부재하면 Concept 섹션에
> [출처 미확인]주석 달고 진행 - 코드 예시 검증 불가면 Pitfalls에 "실제 환경에서 검증 필요" 명시
재호출 지침
Full re-run
- 새 beats 또는 사용자 명시 요청 시 note.md 전체 재작성.
Partial re-run (scope)
오케스트레이터가 scope(예: S1.C2)를 전달하면:
- 기존
note.md가 있으면 input 으로 읽는다. - 5부 구조(Intro/Concept/Example/Pitfalls/Recap) 보존 원칙 — 헤딩과 LO blockquote 는 그대로 유지.
- Cross-ref 안정성 —
[slide K],[S2.C1]참조는 가능한 그대로 유지. slide 번호가 바뀌었으면 (slide-author 재실행 후) 영향받는 ref 만 갱신. - scope 외 class 의
note.md는 건드리지 않는다 (mtime 보존). - 도구 선택 규정: 일부 섹션만 수정할 때는
Edit으로 해당 헤딩 아래 본문만 치환. 전체Write는 사용자 명시 요청 시만. - Diff-before-claim: 섹션별 disposition (preserved / reworded / replaced) 을 보고에 명시. 단순 어휘 교체 vs 의미 변경을 구분.
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 · 84 lines · 41 tokens per session scan A 5c0ee1d119b7
note-writer is an agent published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,090 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.