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.
git clone --depth 1 https://github.com/GktuOktay/ai-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/rules/gktuoktay/ai-skills/apple-design)<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/apple-design"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/apple-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/rules/gktuoktay/ai-skills/apple-design"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/apple-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 | $0.00000 | $0.01359 |
| Opus 5 | $0.00000 | $0.00679 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
apple-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 6d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Human Interface Guidelines (HIG) Skill
Introduction
This skill provides comprehensive guidelines and actionable instructions for building applications that strictly adhere to Apple's Human Interface Guidelines (HIG). The focus is on clarity, deference, and depth, ensuring native-feeling experiences across iOS, macOS, and visionOS.
Core Apple Design Principles
- Clarity: Text is legible at every size, icons are precise and lucid, adornments are subtle and appropriate, and a sharpened focus on functionality motivates the design. Negative space, color, fonts, graphics, and interface elements subtly highlight important content and convey interactivity.
- Deference: Fluid motion and a crisp, beautiful interface help people understand and interact with content without competing with it. Content typically fills the entire screen, while translucency and blurring often hint at more.
- Depth: Distinct visual layers and realistic motion convey hierarchy, impart vitality, and facilitate understanding. Touch and discoverability heighten delight and enable access to functionality and additional content without losing context.
Platform Conventions
iOS Conventions
- Tab Bars: Used for top-level navigation. Must contain between 2 and 5 items. Avoid hiding tab bars when navigating deep into a hierarchy unless absolutely necessary.
- Navigation Bars: Provide drill-down navigation. Use large titles for root views, reverting to standard titles upon scrolling.
- Modals & Sheets: Use sheets for non-blocking contextual tasks. Use full-screen modals for immersive content or complex tasks.
- Safe Areas: Always respect safe areas to prevent content from being clipped by the notch, Dynamic Island, or home indicator.
macOS Conventions
- Window Anatomy: Utilize toolbars, sidebars, and content areas effectively. Sidebars are typically translucent (
NSVisualEffectView). - Menus: Rely heavily on the global menu bar for application commands. Do not duplicate all menu bar actions in the window UI.
- Pointer Interactions: Design for hover states and precise clicking, contrasting with iOS's larger touch targets.
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.
- 6d ago First seen · 109 lines · 1,359 tokens per session scan A 20594444cc7a
apple-design is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,359 tokens. 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 2026-09-03.
Other cursor rules, from other repositories
figma-ios-codegen-workflow
Figma → iOS UIKit codegen workflow. Apply when the user mentions figma / figma.com and wants to convert or generate Swift/UIKit code. Enforces: data package first (preload CLI), bindings maps, full node coverage, audit.json, then coverage + screenshot verification. Do NOT load for unrelated tasks.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.