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 memi-design/design-skills --skill token-architecturegit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/memi-design/design-skills/token-architecture)<a href="https://agentmods.dev/skills/memi-design/design-skills/token-architecture"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/token-architecture/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/memi-design/design-skills/token-architecture"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/token-architecture.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 | $0.00032 | $0.02239 |
| Opus 5 | $0.00016 | $0.01120 |
| Sonnet 5 | $0.00006 | $0.00448 |
| Haiku 4.5 | $0.00003 | $0.00224 |
Grade A, and why
token-architecture 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 8d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Architecture -- Multi-Tier Design Token System
A structured approach to design tokens that scales across platforms, themes, and teams. Tokens are the single source of truth connecting Figma variables, CSS custom properties, Tailwind config, and native platform code.
The Three-Tier Model
Tier 1: Global Tokens (primitives)
--blue-500: #3b82f6
--space-4: 1rem
--radius-md: 8px
Tier 2: Alias Tokens (semantic)
--color-primary: var(--blue-500)
--spacing-component: var(--space-4)
--radius-default: var(--radius-md)
Tier 3: Component Tokens (scoped)
--button-bg: var(--color-primary)
--card-padding: var(--spacing-component)
--input-radius: var(--radius-default)
Why Three Tiers
| Tier | Audience | Changes When |
|---|---|---|
| Global | Token authors | Color palette evolves, spacing scale changes |
| Alias | Theme authors | New theme added, brand refresh |
| Component | Component authors | Component API changes |
A button never references --blue-500 directly. It references --button-bg, which resolves through --color-primary to --blue-500. Changing the brand color only requires updating the alias tier.
Semantic Naming Conventions
Pattern
--{category}-{property}-{element}-{variant}-{state}
All segments after category are optional. Omit segments that do not apply.
Categories
| Category | Purpose | Examples |
|---|---|---|
color |
All color values | --color-bg-primary, --color-text-muted |
spacing |
Margins, paddings, gaps | --spacing-sm, --spacing-page-x |
radius |
Border radii | --radius-sm, --radius-full |
shadow |
Box shadows | --shadow-sm, --shadow-overlay |
font |
Font families | --font-sans, --font-mono |
text |
Font sizes, weights, line heights | --text-sm, --text-heading-weight |
motion |
Durations, easings | --motion-fast, --motion-ease-out |
z |
Z-index layers | --z-dropdown, --z-modal, --z-toast |
size |
Fixed dimensions | --size-icon-sm, --size-avatar-lg |
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.
- 8d ago First seen · 321 lines · 32 tokens per session scan A 640f471421d0
token-architecture is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,239 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 skills, from other repositories
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
motion-craft
Use when an interface moves and the movement has to feel right — durations and easing, what must never animate, fixing motion that reads sluggish, cheap or janky, and reduced-motion. Web and native. NOT the visual system (that is design), NOT the graded critique (that is design-loop).
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…
motion-guide
Use when designing, adding, changing, suggesting, or reviewing UI motion. Motion Guide is a default-trigger motion decision advisor for AI coding agents: it decides whether motion should exist, selects an appropriate functional or expressive pattern, and constrains implementation with timing, easing, accessibility…
motion
Author verified, reduced-motion-safe web animation with MotionSpec. Use when adding scroll, entrance, hover, or loop animation to a website or web app — instead of hand-writing GSAP or CSS keyframes, write a MotionSpec JSON spec, validate it, and compile deterministic code.
canon-interaction
Use when designing or auditing interactive states (hover, focus, active, disabled, loading), focus management, keyboard navigation, click targets, drag-and-drop, or any user input handling. Trigger when the user mentions states, focus, hover, keyboard, interaction, click, tap, or fixing how something responds.