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 sukirman1901/frontend-expert --skill design-vocabularygit clone --depth 1 https://github.com/sukirman1901/frontend-expertWrote 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/sukirman1901/frontend-expert/design-vocabulary)<a href="https://agentmods.dev/skills/sukirman1901/frontend-expert/design-vocabulary"><img src="https://agentmods.dev/badge/skills/sukirman1901/frontend-expert/design-vocabulary/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/sukirman1901/frontend-expert/design-vocabulary"><img src="https://agentmods.dev/badge/skills/sukirman1901/frontend-expert/design-vocabulary.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 | $0.00073 | $0.01971 |
| Opus 5 | $0.00036 | $0.00986 |
| Sonnet 5 | $0.00015 | $0.00394 |
| Haiku 4.5 | $0.00007 | $0.00197 |
Grade A, and why
design-vocabulary 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 11d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Vocabulary
Overview
Bridge the gap between casual descriptions and precise design terms. When a user (or you) describes a UI concept loosely, look it up here before implementing.
When to use
- User describes a UI element informally ("yang ngambang itu", "efek kaca")
- You need the precise term to search
references/or implementation patterns - Communicating design decisions in a handoff or audit
When to skip
- User already uses the correct term
- Pure code fix with no design concept involved
Lookup table
Layout & Structure
| Description (loose) | Term | Definition |
|---|---|---|
| Cards in different sizes grid | Bento grid / Masonry | Asymmetric grid where items have varied sizes |
| Zig-zag text and image | Alternating layout | Rows alternate image-left/image-right |
| Content in the center, nothing on sides | Centered container / Max-width wrapper | Content constrained to a max-width, centered |
| Two columns, one narrow one wide | Sidebar layout / Holy grail | Classic sidebar + main content split |
| Full-width edge-to-edge | Full-bleed | Content extends to viewport edges |
| Overlapping elements | Z-stack / Overlapping composition | Elements layered via absolute/grid overlap |
| Split screen half and half | Split hero / 50-50 layout | Two equal panels side by side |
| Sticky thing that follows scroll | Sticky element | position: sticky — stays in view within parent |
| Content that pins while other scrolls | Scroll-linked pinning | One panel fixed while adjacent content scrolls |
| Cards that can be dragged to reorder | Drag-and-drop sortable | Reorderable list/grid via drag interaction |
Components & Patterns
| Description (loose) | Term | Definition |
|---|---|---|
| Popup that asks "are you sure?" | Confirmation dialog / Alert dialog | Modal requiring explicit confirm/cancel |
| Small notification that auto-hides | Toast / Snackbar | Temporary status message, auto-dismisses |
| Menu that appears on right-click | Context menu | Action menu anchored to pointer position |
| Box floating near a button | Popover / Tooltip | Non-modal overlay anchored to a trigger |
| Menu from the side | Drawer / Sheet / Sidebar panel | Slide-in panel from screen edge |
| Bottom sheet on mobile | Bottom sheet | Drawer that slides up from bottom on mobile |
| Dot on an icon showing count | Badge / Notification badge | Small count/status indicator on an element |
| Expandable section with arrow | Accordion / Disclosure | Collapsible content section with toggle |
| Tabs but vertical | Vertical tabs / Tab rail | Tab navigation stacked vertically |
| Stepper showing progress | Stepper / Wizard progress | Multi-step form progress indicator |
| Chips you can select/remove | Tag / Chip / Pill | Compact element for input, filter, or display |
| Search with dropdown suggestions | Combobox / Autocomplete | Input + filtered suggestion dropdown |
| Toggle that slides | Switch / Toggle | Binary on/off control with sliding thumb |
| Skeleton boxes before content loads | Skeleton screen / Placeholder | Animated loading placeholders mimicking layout |
| Lightbox for images | Lightbox / Image modal | Full-screen overlay for viewing images |
| Infinite scroll | Infinite scroll / Pagination by scroll | Load more items when nearing bottom |
| Breadcrumb trail | Breadcrumbs | Hierarchical navigation trail (Home > Category > Item) |
| Floating button bottom-right | FAB (Floating Action Button) | Persistent primary action floating on page |
| Card with image on top | Media card / Card with hero | Card component with prominent top image |
| Data table with sorting | Data table / Data grid | Table with sort, filter, pagination features |
| Command palette (Cmd+K) | Command palette / Command bar | Quick-action search overlay |
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.
- 11d ago First seen · 149 lines · 73 tokens per session scan A 140a42d96c3d
design-vocabulary is a skill published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,971 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.