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 RBraga01/builder-design --skill design-token-auditgit clone --depth 1 https://github.com/RBraga01/builder-designWrote 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/rbraga01/builder-design/design-token-audit)<a href="https://agentmods.dev/skills/rbraga01/builder-design/design-token-audit"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/design-token-audit/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/rbraga01/builder-design/design-token-audit"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/design-token-audit.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 | $0.00053 | $0.01590 |
| Opus 5 | $0.00026 | $0.00795 |
| Sonnet 5 | $0.00011 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
design-token-audit 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 9d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Token Audit
The Law
HARDCODED VALUES IN AI COMPONENTS ARE DESIGN SYSTEM DEBT.
"#3b82f6 is fine for now" is a value that diverges on the next rebrand and becomes the pattern every developer copies until there are 40 hardcoded blues in the codebase.
Every colour, spacing, typography, shadow, and border radius referencing a token IS a token-compliant component.
When to Use
Trigger before:
- Merging any PR that introduces new AI feature UI components
- Adding new visual styles (colours, spacing, shadows) to existing components
- Launching a new AI feature into a product with an existing design system
- Conducting a design system health check
When NOT to Use
- New products with no design system yet (define tokens first, then this skill applies)
- Prototypes explicitly scoped as throwaway
The Token Categories
Every AI component must reference tokens for all five categories:
1 — Colour Tokens
/* ✗ Hardcoded — fails audit */
color: #3b82f6;
background: rgba(239, 68, 68, 0.1);
border: 1px solid #e5e7eb;
/* ✓ Token-compliant — passes audit */
color: var(--color-primary);
background: var(--color-error-subtle);
border: 1px solid var(--color-border);
AI-specific colour tokens that must exist:
--color-ai-response-bg /* Background for AI response containers */
--color-ai-streaming /* Streaming cursor colour */
--color-ai-uncertain /* Uncertainty indicator (amber family) */
--color-ai-citation /* Citation highlight colour */
--color-ai-error /* AI-specific error (may differ from system error) */
2 — Spacing Tokens
/* ✗ Fails */
padding: 12px 16px;
gap: 8px;
/* ✓ Passes */
padding: var(--space-3) var(--space-4);
gap: var(--space-2);
All spacing must follow a scale (4px base, or 8px base). Arbitrary values (13px, 22px, 37px) are automatic failures.
3 — Typography Tokens
/* ✗ Fails */
font-size: 14px;
font-weight: 500;
line-height: 1.6;
/* ✓ Passes */
font-size: var(--text-sm);
font-weight: var(--font-medium);
line-height: var(--leading-relaxed);
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.
- 9d ago First seen · 185 lines · 53 tokens per session scan A 3a0daaa897d2
design-token-audit is a skill published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,590 once invoked, about $0.0003 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
uxi
UX research and UI design guidance for any product in any domain. Use this whenever the work touches interface design, usability, design critique, accessibility, design systems, user research, information architecture, onboarding, forms, dashboards, landing pages, empty and error states, or interface copy. Trigger it…
ui-designer
!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/visual-grounding.md 2>/dev/null || echo "=== Visual Grounding not loaded ===" !cat skills/shared/protocols/visual-evidence-library.md 2>/dev/null || echo "=== Visual Evidence Library…
ux-principles-skill
Apply established UX, interaction-design, and visual-design principles when designing, building, or reviewing any user-facing interface or flow. Use when creating or editing UI components, screens, forms, navigation, or layouts; when making product/interaction decisions (goals, personas, postures, states); when…
ui-styles
An offline library of 79 UI style families, with prompts in Chinese and English. It covers styles such as glassmorphism, vaporwave, bento grids, and minimalism.
stitch-design
Automate high-fidelity UI prototyping with Google Stitch MCP. Use when the user needs to generate, iterate, or refine UI screens via Stitch prompts.
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".