UX/UI Agent Skills is a set of instructions, design tokens, reusable components, accessibility rules, and design-system references that guide Claude in producing interface designs and code. It is intended for developers and designers who want framework-independent, token-based UI work with accessibility checks. The catalogue entries package these UX, UI, component, and validation workflows as Claude Code skills and related add-ons.
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 plugin87/ux-ui-agent-skills --skill design-codegit clone --depth 1 https://github.com/plugin87/ux-ui-agent-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/plugin87/ux-ui-agent-skills/design-code)<a href="https://agentmods.dev/skills/plugin87/ux-ui-agent-skills/design-code"><img src="https://agentmods.dev/badge/skills/plugin87/ux-ui-agent-skills/design-code/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/plugin87/ux-ui-agent-skills/design-code"><img src="https://agentmods.dev/badge/skills/plugin87/ux-ui-agent-skills/design-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00078 | $0.01741 |
| Opus 5.5 | $0.00031 | $0.00696 |
| Sonnet 5.5 | $0.00016 | $0.00348 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
design-code 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 18d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Design Code
Step 0 — is the kit here? This skill reads files from the kit. Check once:
ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSINGOnKIT_MISSINGonly the skill folders were installed, which is whatnpx skills adddoes. Say so plainly, point the user atnpx ux-ui-agent-skills initor the plugin install, and stop. Do not guess the contents of a file you could not open.
Render components into a target framework via the adapter system.
Steps
- Identify the target framework + styling method from the request (or ask).
- Read
${CLAUDE_SKILL_DIR}/../../../frameworks/adapter-protocol.md(the universal contract: token resolution, component contract, styling, dark mode, motion + output rules). - Load the concrete adapter:
- Full references:
${CLAUDE_SKILL_DIR}/../../../frameworks/react-tailwind.md,${CLAUDE_SKILL_DIR}/../../../frameworks/nextjs.md,${CLAUDE_SKILL_DIR}/../../../frameworks/swiftui.md. - Concise adapters:
${CLAUDE_SKILL_DIR}/../../../frameworks/adapters/{vue,svelte,angular,solid,web-components-lit,react-native,flutter,jetpack-compose,vanilla-css,css-in-js}.md. - No file for the target? Generate an adapter on the fly using the protocol's "author a new adapter" checklist.
- Full references:
- Pull the component spec from
${CLAUDE_SKILL_DIR}/../../../components/*and the ARIA pattern from${CLAUDE_SKILL_DIR}/../../../accessibility/aria-patterns.md. - Resolve all values to tokens (
${CLAUDE_SKILL_DIR}/../../../tokens/*.json); apply aesthetic direction if requested (apply-aestheticskill).
Output rules (mandatory)
Use tokens (never hardcode) · include a11y on every interactive element · handle all applicable of the 8 states · support dark mode at the semantic layer · mobile-first · honor reduced motion · deliver complete files, no placeholders (${CLAUDE_SKILL_DIR}/../../../workflows/redesign-audit.md → Output Completeness).
Verification (mandatory before declaring done)
Code is the highest-stakes output — self-check every time:
- No hardcoded values — every color/size/radius/shadow/duration/font traces to a token (CSS var / theme key / asset). Run
${CLAUDE_SKILL_DIR}/../../../scripts/lint_hardcodes.pyover the output; zero raw hex/px/ms AND zero raw Tailwind palette utilities (bg-gray-500,text-blue-600) — use semantic utilities/tokens (bg-surface,text-primary). Run${CLAUDE_SKILL_DIR}/../../../scripts/validate_theme_refs.pyso everyvar(--…)resolves to a defined theme token (no floating tokens). One allowed exception: 3rd-party theme-config (MUI/Mantine) mapping our tokens INTO their API. - All applicable states present — Default, Hover, Focus(-visible ring), Active, Disabled, Loading(+
aria-busy), Error, Selected — or justified N/A. - Accessibility wired — correct role/ARIA per
${CLAUDE_SKILL_DIR}/../../../accessibility/aria-patterns.md, keyboard model, focus management, ≥24px target; verify contrast (${CLAUDE_SKILL_DIR}/../../../scripts/contrast.py) for any new color pair. - Dark mode + reduced motion + responsive — semantic tokens swap; motion has a
prefers-reduced-motionfallback; layout is mobile-first. - Completeness — full files, no
// ...; if asked for N, deliver N. If any check fails, fix before returning (runa11y-auditif unsure). - Single-theme consistency — consume the project's ONE shared token theme (the root CSS-var layer); never define a per-page palette or new colors. Across multiple pages/screens, the same semantic tokens must drive every surface so the whole product stays visually identical and themeable from one place (
.claude/rules/tokens-and-color.md→ Single-Theme Consistency). - One shared primitive layer — build ONE reusable component per atom (
Button,Input,Modal,Badgeviacva/equivalent); never repeat utility-class clusters inline across files or hand-roll a div-as-modal per screen. Overlays reuse the singleModalprimitive: focus trap,role="dialog",aria-modal="true",aria-labelledby, Escape, return focus on close, backdrop (WCAG 2.4.3 + 2.1.2). See${CLAUDE_SKILL_DIR}/../../../examples/golden/Button.tsx+${CLAUDE_SKILL_DIR}/../../../examples/golden/Modal.tsx. - Font loading — NEVER
@importweb fonts in CSS (render-blocking). Use a framework loader (next/font) or<link rel="preconnect">+<link rel="preload">withfont-display: swap; self-host when possible. Font family comes from a token (--font-sans), never a literal. - Semantic token BY INTENT + consistency — the token's meaning must match the action: destructive (Delete/Remove) →
action.destructive(danger), neveraction.primary; secondary = neutral outline/transparent with dark text (never a colored fill → no dark-text-on-blue). The SAME action uses the SAME variant everywhere (a trigger button and its confirm button must match — not red in one place and blue in another). Gates don't catch this — you must. - No emoji as icons — use a real icon set (default lucide) as inline SVG with
currentColor; never an emoji, including in JS that swaps a label (swap the<svg>, not a text/emoji string). Mentally run${CLAUDE_SKILL_DIR}/../../../scripts/lint_taste.py(it flags emoji-as-icon). - Destructive confirmation UX — irreversible actions (delete account/data, anything stated "cannot be undone") need real friction per WCAG 3.3.4 / 3.3.6: a confirmation dialog whose confirm button restates the action ("Delete account", not "Delete"/"OK"/"Yes") and, for high-stakes, a type-to-confirm step. See
${CLAUDE_SKILL_DIR}/../../../examples/sample-app/preview.htmland${CLAUDE_SKILL_DIR}/../../../content/voice-tone.md. - Taste pre-flight — run the 12-point aesthetic check in
${CLAUDE_SKILL_DIR}/../../../taste/design-taste.mdand, for any rendered HTML,node ${CLAUDE_SKILL_DIR}/../../../scripts/taste_audit.mjs <file>(render-based: flags timid type-scale contrast, uniform repetition, over-wide measure, palette sprawl). Taste is heuristic — treat findings as a strong signal and pair with a real screenshot review; it is NOT auto-provable like correctness. - Run the gates, then report (mandatory). Before declaring done, RUN
node ${CLAUDE_SKILL_DIR}/../../../scripts/verify_states.mjs <file>+--dark(every element, default/hover/focus) andnode ${CLAUDE_SKILL_DIR}/../../../scripts/accuracy_report.mjs; report their actual output. Never type a contrast number or "100%" you didn't just measure (CLAUDE.md → Verification Protocol).
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.
- 18d ago Changed · +6 lines b8e10856ab16
- 1mo ago First seen · 39 lines · 78 tokens per session scan A 19e634d32d28
design-code is a skill published in the GitHub repository plugin87/ux-ui-agent-skills (2,979 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 1,741 once invoked, about $0.0003 per session on Opus 5.5. 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
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".
component-family-consistency
Buttons, inputs, badges and pills share radius, colour logic, shadow, border and spacing. Use when building or reviewing a component library.
extract-design
Extract colours, typography, spacing, components and W3C design tokens from a live website with Dembrandt. Use when you need a site's real tokens or want to seed a design system from it.
modular-scale-typography
Ratio-based type scale where every size relates to the others. Use when defining font sizes or type tokens, or when typography feels arbitrary.
data-display-and-selection
View modes, row selection, mass actions, sorting, filters, search and table patterns. Use when designing data tables, listings, file browsers or any collection.
modal-and-overlay-patterns
Modals, drawers, bottom sheets and popovers, each with its scope and blocking level. Use when designing dialogs, confirmations, side panels or action sheets.