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/macintog/codex-spine/tufte-visualizationnpx skills add macintog/codex-spine --skill tufte-visualizationgit clone --depth 1 https://github.com/macintog/codex-spineWrote 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/macintog/codex-spine/tufte-visualization)<a href="https://agentmods.dev/skills/macintog/codex-spine/tufte-visualization"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/tufte-visualization.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 | $0.00095 | $0.02249 |
| Opus 5 | $0.00048 | $0.01125 |
| Sonnet 5 | $0.00019 | $0.00450 |
| Haiku 4.5 | $0.00010 | $0.00225 |
Grade A, and why
tufte-visualization 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tufte Visualization
Design evidence displays that help a capable reader compare, question, verify, and think. Preserve data resolution and useful context; remove decoration that competes with them. This is a Tufte-inspired reasoning standard, not a recipe for imitating a recognizable Tufte aesthetic.
Derive principles. Do not copy protected book pages, proprietary examples, or another designer's finished visual artifact.
Evidence Contract
- Show what was measured. Preserve metric definitions, units, grain, denominators, time windows, source context, missingness, and transformations.
- Support a named comparison. Use position on common scales, meaningful order, direct labels, small multiples, and visual tables before novelty.
- Make uncertainty proportional to the claim. Distinguish observation, estimate, model output, forecast, and causal inference.
- Integrate words, numbers, and graphics. Put definitions, annotations, source notes, and caveats beside the evidence they qualify.
- Increase information density without flattening hierarchy. Give each figure one dominant comparison, then retain the detail needed to audit it.
- Keep the default view complete. Do not hide essential labels, units, caveats, denominators, or sources in hover, filters, legends, or presenter narration.
- Prove the rendered result. Source validity and successful export are inputs to QA, not substitutes for inspecting the final artifact.
Workflow
1. Frame The Reading Situation
- Name the question, comparison, or decision the display must support.
- Identify the unit of analysis: what one point, row, line, area, or node means.
- Record the audience, medium, final dimensions, viewing distance, ambient conditions, interaction model, and expected reading time when they matter.
- Inspect the host publication, product, or report. Preserve its established typography, palette, and chart conventions unless they compromise integrity, comparison, legibility, or accessibility.
- Select a visual genre and finish bar: academic plate, technical atlas, operational monitor, presentation figure, or interactive analytical view. The medium and use decide the genre; the word "Tufte" does not.
What ships with it
8 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.
- 4d ago First seen · 206 lines · 95 tokens per session scan A 507ab268de40
tufte-visualization is a skill published in the GitHub repository macintog/codex-spine (9 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 2,249 once invoked, about $0.0005 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
frontend-specialist
前端开发专家。用于前端应用、页面、组件、现有 UI 增量改进、已有页面视觉优化、UI/UX 改造、视觉重设计、响应式布局、表单和输入框视觉一致性、设计系统落地、React/Vue/Next.js/Nuxt、Tailwind、shadcn/ui、Radix、MUI、AntD、仪表盘、SaaS、Landing Page、移动端适配、前端性能优化、浏览器截图检查和去除 AI 味 UI。触发后应把“做好看”转化为可执行设计约束，优先复用项目现有组件与视觉语言，小步实现并尽量通过浏览器或 Playwright 做视觉反馈闭环；当用户要改进当前页面或已有界面时，默认先诊断再做局部优化，而不是从 0 重做。.
accessibility-basic-check
Run a basic accessibility checklist for UI changes. Use when a junior developer needs quick a11y guidance.
cli-ux-improver
Improve CLI help, errors, and output. Use when a mid-level developer needs to make a CLI friendlier.
edgespark-frontend-design
Design and redesign EdgeSpark frontends with distinctive, production-grade visual direction instead of generic AI-looking UI. Use when building or polishing landing pages, marketing sites, dashboards, auth flows, portfolios, product surfaces, or reusable frontend sections in EdgeSpark, especially when the task…
brandfetch-automation
Automate Brandfetch tasks via Rube MCP (Composio). Always search tools first for current schemas.
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.