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 skills add HugoVeltorai/publicskills --skill tufte-vizgit clone --depth 1 https://github.com/HugoVeltorai/publicskillsWrote 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/hugoveltorai/publicskills/tufte-viz)<a href="https://agentmods.dev/skills/hugoveltorai/publicskills/tufte-viz"><img src="https://agentmods.dev/badge/skills/hugoveltorai/publicskills/tufte-viz/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/skills/hugoveltorai/publicskills/tufte-viz"><img src="https://agentmods.dev/badge/skills/hugoveltorai/publicskills/tufte-viz.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 | $0.00234 | $0.01447 |
| Opus 5 | $0.00117 | $0.00724 |
| Sonnet 5 | $0.00047 | $0.00289 |
| Haiku 4.5 | $0.00023 | $0.00145 |
Grade A, and why
tufte-viz 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 12d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tufte Data Visualization
Apply Edward Tufte's principles to produce clear, honest, high-density visualizations, and to critique existing ones. The goal is always the same: maximize the information the viewer extracts per unit of ink and pixel, while never distorting what the data say.
Core stance
Before drawing anything, hold three questions in mind. What comparison is the viewer meant to make. What is the single insight that must survive a glance. Who is reading it and at what distance. A chart that cannot answer "compared to what?" is usually the wrong chart.
The default aesthetic is restraint. Start from almost nothing and add only marks that carry data. Grayscale is the baseline; color is reserved for encoding a variable or flagging one thing that matters. If an element can be erased without losing information, erase it.
Workflow for building a new visualization
-
Clarify the data story. Identify the key comparison, the headline insight, and the audience. Write it in one sentence before choosing a chart type. If the data are multivariate, resist collapsing to a single variable just to simplify, because the interaction is often the point.
-
Select the approach using the principles rather than habit:
- High need to compare across categories, periods, or conditions → small multiples (identical scales, identical encoding, tight spacing).
- Dense data where precise values matter → a well-set table, often beating a chart.
- Trend or shape across time → line chart with a muted or absent grid; consider a range-frame axis that spans only the actual data.
- Many metrics at once, shape mattering more than exact value → sparklines, one row per metric with the current value and delta beside it.
- Part-to-whole → bar or table, almost never a pie, and never a 3D pie.
- Causality or mechanism → put the intervention and the response in one frame and annotate the mechanism directly.
-
Design with data-ink in mind. Begin minimal. Every gridline, tick, border, and label must earn its place. Push secondary elements (grids, reference lines, axes) into the background by lightening them so the data dominate; this is layering, and it lets dense displays stay readable.
What ships with it
4 files 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.
- 12d ago First seen · 76 lines · 234 tokens per session scan A ae95a5643d1c
tufte-viz is a skill published in the GitHub repository HugoVeltorai/publicskills (9 stars, last pushed 3mo ago), licensed MIT. It adds 234 tokens to every session and 1,447 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
image-to-svg
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork…
json-render-ui
Generate guardrailed UI from natural language. Emits constrained JSON that a Preact runtime renders. Use when the request is for a dashboard with metrics, charts, or tables; an admin panel; a data visualization interface; or a form-based application.
svg-portrait-mode
Portrait Mode for SVGs — foveated vectorization with 4-zone selective detail. Combines vision annotations, MediaPipe segmentation/landmarks, and optional saliency. Like phone portrait mode, but vectorized. Use when vectorizing a portrait or photo where subject detail should outrank background detail.
strategy-consulting-visualization
Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.
high-quality-slides
A method for creating polished presentation slides, including HTML slide decks, with research, a clear story, chosen visuals, and fixed layouts.