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/slide-authoringnpx skills add tobyilee/course-builder --skill slide-authoringgit 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/slide-authoring)<a href="https://agentmods.dev/skills/tobyilee/course-builder/slide-authoring"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/slide-authoring.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 | $0.00057 | $0.01661 |
| Opus 5 | $0.00028 | $0.00830 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
slide-authoring 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Authoring — Marp Markdown
slide는 Marp Markdown으로 작성한 뒤 marp CLI로 HTML 렌더한다. AI가 raw HTML을 직접 쓰면 레이아웃이 깨지기 쉬우므로 반드시 Marp MD 경유.
Marp 프론트매터 표준
---
marp: true
theme: default
paginate: true
footer: "LO-X.Y"
style: |
section { font-size: 28px; }
h1 { font-size: 42px; }
code { font-size: 22px; }
---
paginate: true— 우하단 페이지 번호footer는 class의 주 LO id. 슬라이드마다 다른 LO면 슬라이드 안에<!-- _footer: "LO-X.Z" -->오버라이드
슬라이드 개수
- class당 4~7장 고정
- 공식:
beats개수 + 1 (제목 슬라이드) + (마무리/recap 1)
슬라이드 레이아웃 규칙 (택1)
각 슬라이드는 다음 3가지 중 정확히 하나만 담는다:
A. Bullet 슬라이드 (3~5 bullet)
## 서버 컴포넌트란
- 서버에서 렌더링되는 React 컴포넌트
- 클라이언트 번들에 포함되지 않음
- DB/파일시스템 직접 접근 가능
- Suspense 경계로 스트리밍됨
B. Code 슬라이드 (≤15줄)
## RSC 예시
~~~jsx
// app/posts/page.js
export default async function Page() {
const posts = await db.query(...);
return posts.map(p => <Post {...p} />);
}
~~~
C. Diagram 슬라이드 (그림/다이어그램)
Mermaid 내장 가능 (default theme 지원):
## 요청 흐름
~~~mermaid
flowchart LR
Browser --> Edge --> Server --> DB
~~~
제목 규칙
- h2 (
##) 사용, h1은 제목 슬라이드에만 - ≤10 단어, 조사 제외
- 질문형/선언형 섞어서 리듬감 (
무엇이 RSC인가→RSC는 어디에 쓰는가→RSC 예시)
Overflow 방지
- 텍스트 총량 ≤80 단어/슬라이드 (ko 기준 160자)
- 코드 ≤15줄, 초과 시 분할 +
(이어서)서브타이틀 - 이미지 문법 정확히 준수할 것 — Marp 는 alt + dimension 을 space-separated로만 인식한다:
— alt 만— dimension 만 (w:NUMBER, h:NUMBER — px 단위 없이 숫자만)— alt + dimension (dimension 은 항상 마지막, space-separated)- 금지:
—alt:prefix 는 Marp가 인식 못해 통째로 plain text 로 렌더됨 (과거 실전 사고) - 금지:
—width:가 아니라w:, 단위는 생략
data:URI 사용 금지 — Marp 는 보안 정책상data:image/...URL 을 모든 형식(utf8,·base64,)에서 통째로 거부한다 (verified with marp-cli v4.3.1:→<img>태그 생성 안 됨, 원본 markdown 이<p>로 래핑되어 슬라이드에 raw text 노출). 인라인 다이어그램이 필요하면 SVG/PNG 를slides_png/diag-NN.svg같은 실제 파일로 저장하고 상대경로로 참조할 것:
Marp 는--allow-local-files플래그(build-bundle.sh 에 이미 포함)로 로컬 파일 SVG 를 PNG 렌더 시 인라인화한다.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 153 lines · 57 tokens per session scan A 85c9a82071a5
slide-authoring is a skill published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,661 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
baoyu-comic
Knowledge comics (知识漫画): educational, biography, tutorial.
html-ppt-zhangzara-cartesian
An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
edu-math-tutorial
数学题分步讲解视频的领域知识。适用场景:(1) 用户给出一道数学题并要求做讲解/ 解题视频;(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"; (3) 需要中文数学教学视频,涉及方程、公式或几何图形。本 skill 只提供领域 知识(题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格);画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。.
style-clone
Building a new course inside someone else's deck — import the deck as a library of layouts, then produce each page of the new course by copying the layout that fits it and rewriting that copy's content element by element, so the result reads as though the original author made it. Use when the session has an imported…
ljg-classic
古文逐字注解、组合排版、章节意旨图与全章解读生成器。把原文、字词注、句义注、无字顶部配图和章节解读排成一张可读的长 PNG。USE WHEN 用户调用 ljg-classic OR 要求给文言文、古诗文、经史子集做逐字注解、彩色夹注、章节解读、古文讲义图、章节配图。NOT FOR 只翻译一句古文、只写现代文章或通用内容卡片。.