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/zinxj/uikit-expert-skill/uikit-expertnpx skills add zinxj/uikit-expert-skill --skill uikit-expertgit clone --depth 1 https://github.com/zinxj/uikit-expert-skillWrote 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/zinxj/uikit-expert-skill/uikit-expert)<a href="https://agentmods.dev/skills/zinxj/uikit-expert-skill/uikit-expert"><img src="https://agentmods.dev/badge/skills/zinxj/uikit-expert-skill/uikit-expert.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 | $0.00095 | $0.04407 |
| Opus 5 | $0.00048 | $0.02204 |
| Sonnet 5 | $0.00019 | $0.00881 |
| Haiku 4.5 | $0.00010 | $0.00441 |
Grade A, and why
uikit-expert 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UIKit Expert Skill
Overview
Use this skill to build, review, or improve UIKit features with correct lifecycle management, performant Auto Layout, modern collection view APIs, and safe navigation patterns. Prioritize native APIs, Apple's documented best practices, and performance-conscious patterns. This skill focuses on facts and best practices without enforcing specific architectural patterns (no MVVM/VIPER/Coordinator mandates).
Workflow Decision Tree
1) Review existing UIKit code
- Check view controller lifecycle usage —
viewIsAppearingfor geometry,viewDidLoadfor setup only (seereferences/view-controller-lifecycle.md) - Verify Auto Layout correctness — batch activation, no constraint churn,
translatesAutoresizingMaskIntoConstraints(seereferences/auto-layout.md) - Check collection/table view APIs — diffable data sources, stable identity, CellRegistration (see
references/modern-collection-views.md) - Verify cell configuration uses
UIContentConfiguration, not deprecatedtextLabel(seereferences/cell-configuration.md) - Check list scroll performance — prefetching, cell reuse cleanup, reconfigureItems (see
references/list-performance.md) - Verify navigation patterns — bar appearance all 4 slots, no concurrent transition crashes (see
references/navigation-patterns.md) - Check animation correctness — API selection, PropertyAnimator state machine, constraint animation (see
references/animation-patterns.md) - Audit memory management —
[weak self], delegate ownership, Timer/CADisplayLink traps (seereferences/memory-management.md) - Check concurrency safety — Task lifecycle, cancellation in viewDidDisappear (see
references/concurrency-main-thread.md) - If SwiftUI interop present — verify UIHostingController containment, sizingOptions (see
references/uikit-swiftui-interop.md) - Check image loading — downsampling, cell reuse race condition (cancel/clear/verify) (see
references/image-loading.md) - Verify keyboard handling — UIKeyboardLayoutGuide over manual notifications (see
references/keyboard-scroll.md) - Check trait handling and accessibility — registerForTraitChanges, Dynamic Type, VoiceOver (see
references/adaptive-appearance.md) - Validate modern API adoption and iOS 26+ availability handling (see
references/modern-uikit-apis.md)
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/adaptive-appearance.md 28 KB
- references/animation-patterns.md 30 KB
- references/auto-layout.md 34 KB
- references/cell-configuration.md 29 KB
- references/concurrency-main-thread.md 26 KB
- references/image-loading.md 27 KB
- references/keyboard-scroll.md 30 KB
- references/list-performance.md 30 KB
- references/memory-management.md 26 KB
- references/modern-collection-views.md 29 KB
- references/modern-uikit-apis.md 23 KB
- references/navigation-patterns.md 29 KB
- references/skill-expert-uikit-v3.2-beta.5.zip 565 KB
- references/uikit-swiftui-interop.md 26 KB
- references/view-controller-lifecycle.md 24 KB
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 · 281 lines · 95 tokens per session scan A c71de7d11922
uikit-expert is a skill published in the GitHub repository zinxj/uikit-expert-skill (5 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 4,407 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
compose-modernize-build
Modernize an Android project's Gradle build: bump to Kotlin 2.x with kotlin-compose plugin (replace kotlinCompilerExtensionVersion), migrate kapt to KSP, introduce Version Catalogs (libs.versions.toml), use the Compose BOM, switch to Material 3.
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…
swiftui-view-architect
Refactor oversized SwiftUI view files into stable, dedicated subviews with MV-first data flow, explicit dependencies, extracted actions, and correct Observation usage.
flutter-codestyle
Custom Instructions: Senior Flutter & Dart Engineer.
ios-agent-skill
Expert iOS/Swift developer behavior for AI coding agents. Use when writing, reviewing, or refactoring Swift, SwiftUI, UIKit, or SwiftData code; when designing iOS app architecture (MVVM, Clean Architecture, coordinators, routing); when building UI that must meet Apple's Human Interface Guidelines, contrast, dark-mode…
bootstrap-ios
Bootstrap agents for iOS, iPadOS, macOS, Swift, SwiftUI, SwiftData/Core Data, Swift Testing, Xcode build/test/debug, Simulator, App Intents, or XcodeBuildMCP work. Use before building, fixing, refactoring, QAing, or setting up Apple-platform repos, and when asked to load/install Ray's iOS skills or bootstrap iOS.