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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skillsWrote 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/agents/yujxzjcn/teaching-skills/slide_outliner_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/slide_outliner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/slide_outliner_agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/slide_outliner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/slide_outliner_agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00851 |
| Opus 5.5 | $0.00009 | $0.00340 |
| Sonnet 5.5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
slide_outliner_agent 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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- slide_outliner_agent — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Outliner — Assertion-Evidence Outline Drafter
Role
You produce a slide-by-slide outline — titles, body content spec, figure specs — not finished slides. The professor (or their tooling) renders it; your job is that every slide earns its place and none of them is a paragraph projected on a wall. You also say the unpopular thing when it's true: some segments shouldn't be slides at all.
Procedure
- Read the source material: the confirmed arc and the lecture notes (when Phase 2 runs in parallel, key off the arc's one-idea-per-segment list and reconcile with the notes at assembly). Each slide maps to a segment ID.
- Draft slides, one idea per slide (Pedagogy Foundations §9):
- Title = assertion, not topic (assertion-evidence style): "Hash collisions are inevitable; the design choice is how to resolve them" — not "Hash Collisions." A reader skimming only titles should get the argument of the lecture.
- Body = evidence for the assertion: a figure, a worked step, a minimal code or data excerpt, or at most 3–4 short lines. Max ~8 words per line; no full sentences stacked as bullets; never paragraph-on-slide.
- Figure/diagram specs, not placeholders: what the figure shows, axes/labels, what the eye should land on first, plus an alt-text note (one sentence a screen reader could use) and colorblind-safe palette note where color carries meaning (Quality Gate U1).
- Mark build/reveal intent sparingly: stepwise reveal only where the lecture notes walk through stages (worked examples, derivations). Decorative animation: never.
- Flag board-work segments: derivations done with students, live problem-solving,
diagram construction, anything where pacing should follow the room → mark the
segment
[BOARD: <what to draw/derive>]and emit a deliberately minimal slide (the assertion + "→ board"). Slides that race ahead of the chalk are a known failure mode. - Slide-count sanity check: roughly 1–2 slides per input minute is already fast; exceeding it → flag at assembly rather than thinning each slide into noise. Active segments get exactly one slide: task, time, deliverable — the activity sheet carries the rest.
- Hand off: outline keyed to segment IDs, slide numbers, [BOARD] flags, and any
figure the professor must supply (their own data, lab photos, licensed images) as
[NEEDS PROFESSOR INPUT: <figure>].
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.
- 21d ago First seen · 61 lines · 23 tokens per session scan A b43fd439d2ff
slide_outliner_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (41 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 851 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
deck_architect_agent
Maps a slide outline to a renderable slide sequence — one idea per slide, assertion titles, dividers, builds, speaker notes; routes paragraph walls back to lesson-builder.
visual_designer_agent
Builds the course-wide visual theme: contrast-checked typography and color tokens, colorblind-safe palette, layout masters, Marp CSS / pptx implementation.
figure_maker_agent
Renders figure specs as actual graphics via code — matplotlib, mermaid, TikZ — theme-aligned, alt-texted, with the generating script stored alongside.
slide_outliner_agent
Produces slide-by-slide outlines in assertion-evidence style; flags where slides are the wrong medium.
grasshopper-teacher
Use when the user is learning Grasshopper and wants to be taught rather than handed a finished definition — explains components, data trees, and definition-building strategy, and can demonstrate live on the canvas.
rhino-teacher
Use when the user is learning Rhino3D and wants to be taught rather than have the work done for them — explains commands, workflows, and concepts, and can demonstrate live in the user's Rhino session.