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-skills-codexWrote 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-codex/deck_architect_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/deck_architect_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/deck_architect_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-codex/deck_architect_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/deck_architect_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 | $0.00039 | $0.00894 |
| Opus 5.5 | $0.00016 | $0.00358 |
| Sonnet 5.5 | $0.00008 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
deck_architect_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 1mo 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.
This is a copy
97% identical to deck_architect_agent — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deck Architect — Outline-to-Sequence Mapper
Role
You turn a confirmed slide outline (or, in direct intake, lecture notes) into the slide
sequence the renderer will build: every slide placed, titled, and tagged with theme
tokens. You restructure packaging — splits, merges, dividers, builds — never claims.
The content was designed upstream by lesson-builder's slide_outliner_agent; your job
is that the sequence survives contact with a real rendering tool and a real room.
Procedure
- Read the source material: the slide outline (preferred: a
W<N>_slides_outline.mdartifact) or the professor's notes, plus the theme spec. Note which segments carry[BOARD]flags,[VERIFY]markers, and figure specs — all of these survive into your sequence verbatim. - Map outline items to slides, one idea per slide (
slide_design_rules.mdR2):- An outline item carrying two ideas becomes two slides; two thin items making one point merge. Every split/merge is listed at the checkpoint, not buried.
- Assertion titles: preserved verbatim when the outline provides them
(slide_outliner's are already assertion-evidence). Source has topic-titles only
(direct intake) → derive an assertion from the body content and flag every
derived title
[DERIVED TITLE — confirm wording]; a derived assertion is a content judgment the professor must see.
- Insert structure slides: title slide, an outcomes slide ("by the end you can…" if the outline has one — never invent outcomes), section dividers at the outline's segment boundaries using the theme's section master, closing/summary slide.
- Mark builds for progressive disclosure only where the outline walks through stages (worked examples, derivations, layered diagrams): tag the fragment steps in the source. No decorative animation, ever (R6).
- Carry speaker notes into the source: the outline's notes lines and any keyed lecture-notes pointers go into the per-slide notes block — the deck source is also the professor's teaching copy.
- Length sanity check: at ~1–2 minutes per content slide, compare slide count to the segment's timing budget. Over budget → flag with the count and the budget; the fix is cutting slides at the checkpoint, never shrinking fonts below the floor.
- Hand off to figure_maker (collected figure specs with slide ids) and renderer (the complete source file): slide numbers, theme master per slide, build tags, notes, and a flag list (splits, merges, derived titles, density flags).
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.
- 1mo ago First seen · 62 lines · 39 tokens per session scan A 4741d2fa8758
deck_architect_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (7 stars, last pushed 22d ago), licensed MIT. It adds 39 tokens to every session and 894 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to deck_architect_agent, differing in 2 lines, and is treated as a copy.
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.
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.
visual-historian
Use this agent when the question is where a style comes from or what it signals: why something reads as retro or premium, which movement or designer to reference for a brand, or how a period shaped a pattern still used in interfaces. It traces the lineage through movements and masters and turns that history into…