Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kevintsai1202/teaching-site-skillsnpx agentmods add skills/kevintsai1202/teaching-site-skills/teaching-site-design-systemWrote 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/kevintsai1202/teaching-site-skills/teaching-site-design-system)<a href="https://agentmods.dev/skills/kevintsai1202/teaching-site-skills/teaching-site-design-system"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/teaching-site-design-system/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/kevintsai1202/teaching-site-skills/teaching-site-design-system"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/teaching-site-design-system.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 | $0.00181 | $0.04196 |
| Opus 5 | $0.00090 | $0.02098 |
| Sonnet 5 | $0.00036 | $0.00839 |
| Haiku 4.5 | $0.00018 | $0.00420 |
Grade A, and why
teaching-site-design-system 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teaching Site Design System
Token starter (copy this, don't re-derive):
templates/tokens.css— full:rootblock + dark theme + signature components (day-hero, glass-card, prompt-card, task-list, learning-goal, concept, unit, material, table). Paste into the<style>block ofindex.html(vanilla SPA pattern) or use as externalstyle.css.Schema authority: this skill defines visual tokens; data field names live in
_shared/domain-primitives.md. When styling a component, read that file to know the data shape you're rendering.Reference implementation:
d:/GitHub/ai-workshop/index.html:11-1700— the full production CSS this skill's tokens were extracted from.
This skill defines the visual layer of a teaching site: color tokens, typography, geometry, components, dark mode strategy, and — critically — the reasoning behind each decision. The rationale matters more than the literal values; future sites can re-tune the values, but the why survives across projects.
When to Invoke
- Setting up a new teaching site (read tokens before writing first CSS).
- Adding a new visual element (badge, card, hero) — check whether an existing pattern covers it before inventing.
- Tuning dark mode (which token to override, which not to).
- Producing a corporate edition or ebook (same tokens flow to print CSS).
- Reviewing visual consistency complaints ("it looks inconsistent here").
The Foundational Decision: OKLCH, Not HEX/RGB
:root {
--bg: oklch(99% 0.002 240);
--surface: oklch(100% 0 0);
--fg: oklch(18% 0.012 250);
--accent: oklch(58% 0.18 255);
--accent-2: oklch(66% 0.14 65);
}
Why OKLCH (not #1a73e8 or hsl(...)):
- Perceptually uniform —
oklch(60% ...)andoklch(70% ...)look like an equal step apart; HSL doesn't (its 60→70 yellow jumps visually huge but blue barely changes). - Predictable dark mode — for each light token at
L=N%, the dark equivalent is roughlyL=(100-N)%with the same chroma+hue. Mechanical. color-mix(in oklab, ...)works natively — e.g. soft accent tints (color-mix(in oklab, var(--accent) 18%, transparent)) compose cleanly, no manual rgba math.- Modern browser support is fine (Chrome 111+, Safari 15.4+, Firefox 113+). For a static teaching site this is acceptable.
What ships with it
1 file 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 · 341 lines · 181 tokens per session scan A 624d6c3fe2ce
teaching-site-design-system is a skill published in the GitHub repository kevintsai1202/teaching-site-skills (50 stars, last pushed 4mo ago), licensed MIT. It adds 181 tokens to every session and 4,196 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
hps-bauhaus
A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.
html-ppt-zhangzara-playful
A retail sales-floor training on consultative selling — the flow, the role-plays, and the daily habit that lifts conversion. Built as a decision-grade professional training deck for store associates, floor managers.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
html-ppt-zhangzara-scatterbrain
A design-school graduation project: a civic wayfinding system for a transit hub — the brief, the process, and the outcome. Built as a decision-grade coursework defense deck for crit panel, faculty.
frontend-slides
OpenDesign as a worked AI-workflow example: how local agents read your files and design on your desktop — concretely. Built as a decision-grade AI literacy deck for teams new to AI, leadership.