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 evgenii-studitskikh/Claude-Code-SaaS-Studio --skill design-uigit clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-StudioWrote 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/evgenii-studitskikh/claude-code-saas-studio/design-ui)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/design-ui"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/design-ui.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00513 |
| Opus 5 | $0.00019 | $0.00257 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
design-ui 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.
What it actually says
Define the component-level UI specification for every screen in the approved screen list, grounded in shadcn/ui and Tailwind conventions, so that frontend-engineer can build with minimal back-and-forth. Non-autonomous: component choices are proposed and confirmed before the spec is written.
Phases
- Load flows — read
docs/specs/flows.md. If missing, stop and direct to/map-flows. If a specific screen name was passed as an argument, scope this run to that screen only; otherwise process all screens. - Propose layout and components — for each screen, suggest: overall layout pattern (full-page, split-panel, modal, drawer), the primary shadcn/ui components (
Card,DataTable,Form,Dialog, etc.), and any Tailwind utility patterns. Reference shadcn/ui component names exactly so the frontend-engineer can look them up directly. - Specify interaction states — for every screen, explicitly call out: empty state (what the user sees before any data), loading state (skeleton or spinner approach), and error state (inline error, toast, or full-page). Missing these is a common source of rework — do not skip.
- Note accessibility — for each screen note the required ARIA landmarks, focus-trap requirements (for modals/drawers), and any keyboard navigation considerations. Flag any component where shadcn defaults need augmentation.
- Approval gate — under
fullreview, walk through each screen's spec with the user; underleanorsolo, present a summary table and ask for a single sign-off. Do not write until approved. - Write the spec — write
docs/specs/ui.mdwith the approved component decisions. Next step: point to/setup-stack(if scaffold not yet created) or/build-feature.
Output
docs/specs/ui.md — per-screen component spec. Writes nothing else without approval.
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 · 23 lines · 38 tokens per session scan A bdeda5b35d0a
design-ui is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 513 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 2026-08-31.
Other skills, from other repositories
drag-pane
Drag-and-drop pane resizing implementation for two-pane plugin layouts. Covers mouse event handling via the internal/mouse package, hit region registration, drag delta calculation, width clamping, state persistence, and pane layout management. Use when working on pane resizing, drag interactions, layout management, or…
ui-features
Implementing UI/UX features in sidecar including modals (internal/modal library), keyboard shortcuts, mouse support, scrolling, pill/tab rendering, and pane resizing. Use when implementing UI features, handling user input, adding keyboard shortcuts, building modals, or working on UX improvements.
impeccable
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
ui-ux-pro-max
Use when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset and Python search runtime.
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
icon-forge
Generate brand icons as SVG and produce all platform assets including favicon package (ICO, SVG with dark mode, apple-touch-icon), PWA manifest icons, and mobile app icons. Use when user runs /icon-forge, requests "brand icon", "favicon generation", "app icon", or "svg logo" for a project.