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 koshkinvv/ios-agent-skills --skill ios-swiftuigit clone --depth 1 https://github.com/koshkinvv/ios-agent-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/skills/koshkinvv/ios-agent-skills/ios-swiftui)<a href="https://agentmods.dev/skills/koshkinvv/ios-agent-skills/ios-swiftui"><img src="https://agentmods.dev/badge/skills/koshkinvv/ios-agent-skills/ios-swiftui/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/koshkinvv/ios-agent-skills/ios-swiftui"><img src="https://agentmods.dev/badge/skills/koshkinvv/ios-agent-skills/ios-swiftui.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 | $0.00203 | $0.02787 |
| Opus 5 | $0.00102 | $0.01393 |
| Sonnet 5 | $0.00041 | $0.00557 |
| Haiku 4.5 | $0.00020 | $0.00279 |
Grade A, and why
ios-swiftui 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 11d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS SwiftUI Expert Skill
Core Rules
- Use @Observable (iOS 17+) over ObservableObject — fine-grained property tracking, better performance, simpler syntax.
- Use @State to own @Observable instances, NOT @StateObject.
@StateObjectis the pre-iOS 17 pattern. - Use NavigationStack (not NavigationView) with value-based
NavigationLink+.navigationDestination. - Never nest NavigationStack inside NavigationStack — causes double navigation bars and broken behavior.
- Use LazyVStack/LazyHStack inside ScrollView for large collections. Use
Listfor very large datasets (cell reuse + prefetching). - Keep
bodypure — no data processing, network calls, or side effects. Use.taskmodifier for async work. - Avoid
AnyView— it destroys view identity and kills diffing performance. Use@ViewBuilderorGroupinstead. - Preserve view identity — use ternary operators (
condition ? viewA : viewB), notif/elsethat changes the view type in ways that break animations. - Break large views into small subviews — SwiftUI re-evaluates
bodyoften; smaller views = smaller re-evaluation scope. - Use
.equatable()on expensive views to skip unnecessary re-renders.
Decision Tables
State Management — What to Use When
| Scenario | iOS 17+ | Pre-iOS 17 |
|---|---|---|
| Simple value owned by view | @State |
@State |
| Pass value down for read/write | @Binding |
@Binding |
| Reference-type model owned by view | @State + @Observable |
@StateObject + ObservableObject |
| Reference-type model passed in | just pass it (auto-tracked) | @ObservedObject |
| Shared model via environment | @Environment + custom key |
@EnvironmentObject |
| Create binding to @Observable property | @Bindable |
N/A (use @Published + $) |
| System environment values | @Environment(\.colorScheme) |
same |
Key insight: With @Observable, SwiftUI tracks which properties a view actually reads in body. With ObservableObject, ANY @Published change triggers ALL observing views to re-evaluate.
What ships with it
5 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.
- 11d ago First seen · 296 lines · 203 tokens per session scan A eb8837247b21
ios-swiftui is a skill published in the GitHub repository koshkinvv/ios-agent-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 203 tokens to every session and 2,787 once invoked, about $0.0010 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-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
swift-concurrency
Use for any Swift Concurrency question on Apple platforms. Triggers on: actor reentrancy (stale state after await), AsyncStream lifecycle (continuation.finish, onTermination), TaskGroup memory and task throttling (activeProcessorCount), Sendable conformance across actor boundaries (non-Sendable third-party types)…
tca-swiftui
Use for any question about The Composable Architecture (TCA) — defining reducers, managing state, handling navigation, writing tests, or working with dependencies. Essential when encountering TCA-specific types like @Reducer, @ObservableState, StackState, StackAction, @Presents, TestStore, @DependencyClient, Scope, or…
uikit-mvvm
Use for hands-on UIKit MVVM questions: setting up Combine bindings between UIViewController and ViewModel (@Published + sink), extracting business logic from massive ViewControllers step by step, testing ViewModels with XCTestExpectation + Combine publishers, fixing [weak self] retain cycles in sink closures…
kotlin-coroutines-flows
Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.
build-feature
Build an iOS feature using ShipSwift components. Use when the user says "build", "create", "add a feature", or describes an iOS feature they want to implement.