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 agentmods add skills/lenxism/ives/interface-architecturenpx skills add lenxism/ives --skill interface-architecturegit clone --depth 1 https://github.com/lenxism/ivesWhat 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 | $0.00105 | $0.01233 |
| Opus 5 | $0.00053 | $0.00616 |
| Sonnet 5 | $0.00021 | $0.00247 |
| Haiku 4.5 | $0.00011 | $0.00123 |
Grade A, and why
interface-architecture 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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interface Architecture
Getting architecture right means the interface feels intuitive even before it looks beautiful. Getting it wrong means no amount of polish saves it.
Start with Defaults
Ask: "What would default iOS give us?" or "What would shadcn + Tailwind look like?"
This establishes the most conventional, familiar solution — then you optimize.
iOS defaults: Tab bars for peer destinations, table views for lists, push navigation for drill-down, sheets for focused tasks.
Web defaults: Sidebar navigation for apps, top nav for marketing, card grids for browsable content, modals for focused tasks.
The best products — Family, Raycast, Linear — show deep respect for platform conventions while innovating on every aspect. Understand the standard, match it, then exceed it.
Separation of Concerns
Before diving in, identify what question you're answering, then go only as far as needed:
- Architecture: Right interaction model? (Don't need visual design yet)
- Layout: Information structure make sense? (Don't need final content)
- Visual Language: Colors, type, spacing convey right attributes? (Test on isolated components)
- Polish: Details refined? (Only after everything above is resolved)
Working on everything at once leads to rabbit holes and compounding rework. Slow is smooth, smooth is fast.
Fidelity decisions
- Testing interaction model: White cards with shadows, no content. Just the interaction.
- Exploring architecture: Simple boxes and labels. Just the structure.
- Refining visual language: Component playground. Just the aesthetic.
- Shipping: Full fidelity. Everything considered.
Information Architecture
Reduce cognitive load through grouping
A flat list of 40+ items overwhelms. Group into phases, categories, or sections. Natural chunking makes the whole feel manageable.
Progressive disclosure
- Root level: Show phases/categories, not all items
- Drill-down: Items within the selected group
- Detail: Full information for the selected item
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.
- 2d ago First seen · 138 lines · 105 tokens per session scan A 9e97a09c9e8f
interface-architecture is a skill published in the GitHub repository lenxism/ives (5 stars, last pushed 6mo ago), licensed MIT. It adds 105 tokens to every session and 1,233 once invoked, about $0.0005 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
design-guide
Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design…
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.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.