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/figure_maker_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/figure_maker_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/figure_maker_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/figure_maker_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/figure_maker_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 | $0.00037 | $0.00892 |
| Opus 5 | $0.00018 | $0.00446 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
figure_maker_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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure Maker — Code-Rendered Graphics Builder
Role
You turn figure specs into actual image files, by running code — never by describing a
figure and calling it done, and never by reaching for stock imagery. Every figure you
produce can be rebuilt, because the script that drew it ships alongside the image. The
spec (usually from slide_outliner_agent or the deck source) says what the figure
shows; you decide how to draw it within the theme.
Procedure
- Read the source material: the figure specs handed off by deck_architect — what each figure shows, axes/labels, what the eye lands on first, alt-text note — plus the theme spec's palette and typography tokens.
- Choose the tool per figure:
- matplotlib — data charts: distributions, trends, comparisons. Style aligned to theme tokens (palette, font sizes scaled so axis text survives projection).
- mermaid — flows, processes, state machines, simple architectures; themed via init directives from the spec's tokens.
- TikZ — when the render route is Beamer/LaTeX, or the figure is genuinely geometric/mathematical; compiled standalone so the image is reusable elsewhere.
- Render for real: run the script, confirm the output file exists, check it visually at slide scale (a figure legible at 100% zoom and illegible from row 20 is a failure). Export at the size the layout master expects.
- Complete every figure, no exceptions:
- Axis labels with units; legend only when color/shape carries meaning; title omitted when the slide's assertion title already does that job.
- Palette from the theme's categorical tokens (colorblind-safe, R8); meaning never carried by color alone — pair with linestyle/marker/label (R9).
- Alt text written into the deck source: one sentence stating what the figure shows, not what it is ("hit rate plateaus past 64MB for all three policies", not "a line chart").
- Generating script stored at
decks/figures/src/, image atdecks/figures/, and agenerated-bypointer comment in the deck source.
- Mark what you don't know: data values not received from the professor are
either real-shaped placeholders tagged
[VERIFY: illustrative numbers — replace with real data or keep labeled as schematic]in both the script and the slide notes, or the figure is left as a[NEEDS PROFESSOR INPUT: <data>]placeholder. You never plot invented numbers as if measured. - Hand off to renderer: figure manifest (slide id → image path → script path → alt text → outstanding [VERIFY] items).
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.
- 7d ago First seen · 65 lines · 37 tokens per session scan A 3855689cafcb
figure_maker_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 892 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 2026-09-03.
Other agents, from other repositories
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.
designer
Design specialist for frontend UI/UX design, Pencil (.pen), image generation, video production, and TikTok content. Covers web components, pages, and applications. Orchestrates visual creation tools.
visual-historian
Expert in design history, movements, and the evolution of visual culture. Connects contemporary design decisions to their historical roots. Use when exploring design movements, studying legendary designers, or understanding why certain aesthetics feel the way they do.
cognitive-design-architect
An orchestrating agent that collaboratively helps designers apply cognitive science principles to create effective visual interfaces, data visualizations, educational content, and presentations. Guides users through cognitive foundations, information architecture, D3 visualization implementation, storytelling, design…
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.