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 kageroumado/swiftui-macos-skill --skill swiftui-macosgit clone --depth 1 https://github.com/kageroumado/swiftui-macos-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/kageroumado/swiftui-macos-skill/swiftui-macos)<a href="https://agentmods.dev/skills/kageroumado/swiftui-macos-skill/swiftui-macos"><img src="https://agentmods.dev/badge/skills/kageroumado/swiftui-macos-skill/swiftui-macos/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/kageroumado/swiftui-macos-skill/swiftui-macos"><img src="https://agentmods.dev/badge/skills/kageroumado/swiftui-macos-skill/swiftui-macos.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 | $0.00150 | $0.01073 |
| Opus 5 | $0.00075 | $0.00536 |
| Sonnet 5 | $0.00030 | $0.00215 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
swiftui-macos 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide SwiftUI development for macOS apps. Whether writing new code or reviewing existing code, apply deep understanding of SwiftUI's runtime behavior — how the observation registrar dispatches, how the attribute graph diffs view trees, how actor isolation interacts with view lifecycles.
How to Use
Writing code: Load relevant references before implementation. The patterns here prevent bugs that are expensive to find later — observation cascades, identity thrashing, concurrency overhead. When making architecture decisions (state ownership, view decomposition, AppKit bridging), consult the relevant reference for tradeoffs.
Reviewing code: Check each reference area systematically. Focus on genuine problems — observation inefficiencies, deprecated API, accessibility gaps, concurrency anti-patterns. Don't flag obvious issues or invent problems.
Partial scope: Load only what the task needs. Not every change requires all eight references.
References
| Reference | Load when |
|---|---|
references/observation.md |
@Observable, @State, ForEach, data-driven views, Observations {} streams |
references/concurrency.md |
Task, async/await, actors, DispatchQueue, AsyncStream, scheduling decisions |
references/performance.md |
View composition, animations, gestures, large collections, Canvas, TimelineView |
references/views.md |
View decomposition, navigation, .task(id:), preference keys, custom Layout |
references/data.md |
State architecture, SwiftData, environment injection, bindings, persistence |
references/platform.md |
NSViewRepresentable, NSHostingView, multi-window, AppKit bridging, window chrome |
references/api.md |
API choice, deprecated patterns, modern Swift/SwiftUI idioms |
references/accessibility.md |
VoiceOver, keyboard navigation, Dynamic Type, Reduce Motion |
Principles
- Target macOS 26+, Swift 6.2 with strict concurrency and
@MainActordefault isolation. - Check whether the project enables
NonisolatedNonsendingByDefault(SE-0461) — this changes wherenonisolatedasync functions execute. Seereferences/concurrency.md. - Prefer SwiftUI-native solutions. Use AppKit (
NSViewRepresentable,NSHostingView,NSWindow) only when SwiftUI has no equivalent. - Understand the mechanism. When suggesting a pattern, know why it works — what the observation registrar does, what the attribute graph diffing costs, what
_modifyvssetmeans for notification. Rules without understanding produce cargo-culted code. - Do not introduce third-party frameworks without asking. Apple's open-source Swift packages (
swift-collections,swift-algorithms,swift-async-algorithms) are exceptions — prefer them over reimplementing non-trivial data structures or algorithms. Seereferences/api.md.
What ships with it
8 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.
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.
- 10d ago First seen · 62 lines · 150 tokens per session scan A 6dded8c4daad
swiftui-macos is a skill published in the GitHub repository kageroumado/swiftui-macos-skill (11 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 1,073 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
tauri-expert
Expert skill for Tauri (v2) development, Rust backend, IPC, and security / Panduan ahli untuk pengembangan Tauri v2, Rust backend, IPC, dan keamanan.
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.
axiom-concurrency
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
developing-genkit-dart
Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.
wax
Swift framework guidance for Wax on-device memory/RAG. Use when writing Swift code with the public Memory facade, experimental PhotoMemory / VideoMemory, BuiltInMultimodalEmbeddings, embedding providers, retrieval modes, or hybrid search. For agent operators using the Wax MCP server tools, use the separate wax-mcp…