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 HalidSaglam/saglitzdesign-mcp --skill clean-interface-designgit clone --depth 1 https://github.com/HalidSaglam/saglitzdesign-mcpWrote 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/halidsaglam/saglitzdesign-mcp/clean-interface-design)<a href="https://agentmods.dev/skills/halidsaglam/saglitzdesign-mcp/clean-interface-design"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/clean-interface-design/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/halidsaglam/saglitzdesign-mcp/clean-interface-design"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/clean-interface-design.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 | $0.00095 | $0.01470 |
| Opus 5.5 | $0.00038 | $0.00588 |
| Sonnet 5.5 | $0.00019 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
clean-interface-design 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 1mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Interface Design
Most "AI-looking" UI fails the same way: too many colors, too many type sizes, inconsistent radii, no clear primary action, and no breathing room. Fix those and almost anything looks intentional.
Full depth (specs, contrast math, tokens, real examples) is available via the SaglitzDesign MCP (
npx saglitzdesign-mcp) — docsclean-app-design,color-systems,typography,spacing-layout,visual-craft-standards; toolscreate_design_system(one call → the whole foundation),generate_layout_system,generate_design_tokens,audit_accessibility, andaudit_design_systemto measure whether the restraint below actually held.
The rules that do most of the work
- One accent color + its soft tints. Pick a single brand/accent hue. Use it for the primary action and key highlights only (~10% of the surface). Everything else is a neutral ramp. Scarcity is what makes the accent pop.
- Whitespace is a feature. Give elements room to breathe; when unsure, add more space, not more UI. Grouping is communicated by space — gap within a group must be smaller than gap between groups.
- One corner radius system. Pick a radius and apply it consistently to cards, inputs, buttons, and icon containers. Don't mix 4px cards with 16px buttons. Pill buttons pair with pill inputs.
- Two or three type sizes, not five. A tight scale (e.g. 14 / 16 / 24) with weight and color for hierarchy reads far cleaner than five sizes. Express hierarchy with size + weight + color (3 opacity levels), not more fonts.
- One clean font. A single quality family is enough. Good geometric/neutral options: system fonts (SF/Segoe/Roboto), Inter, Geist, Open Runde (free, rounded-geometric). Two families max — a distinctive display + a workhorse body.
- One icon family, one weight. Use a single cohesive set at a single stroke/weight. Good free sets: Solar (incl. duotone), Lucide, Phosphor, Heroicons. Never mix icon families.
- Borders OR shadows — pick one. Choose one system to separate surfaces (borders read better in dark mode; soft shadows on light). Don't stack a border and a shadow and a fill on the same card.
- One primary action per view. Exactly one filled/high-emphasis button per screen or section. Everything else is secondary (tonal/outline) or tertiary (text). Two filled buttons side by side destroy hierarchy.
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.
- 1mo ago Changed · +18 lines 64b71997f1a7
- 1mo ago First seen · 49 lines · 95 tokens per session scan A e5f8ba57c5c7
clean-interface-design is a skill published in the GitHub repository HalidSaglam/saglitzdesign-mcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,470 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
platform-conventions
Design to iOS and Android conventions — what each OS mandates, where they diverge, and when to unify. Use when shipping native apps. For breakpoint adaptation use responsive-design; for matching competitor patterns use jakobs-law (interaction-design).
logo-creator
Create logos using AI image generation. Discuss style/ratio, generate variations, iterate with user feedback, crop, remove background, and export as SVG. Use when user wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo.
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.
design-system-governance
Define how the system evolves — contribution model, versioning, deprecation, and change management. Use when multiple teams contribute. For driving uptake use design-system-adoption (designer-toolkit); for design file history use version-control-strategy (design-ops).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).