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 rusel95/ios-agent-skills --skill swift-concurrencygit clone --depth 1 https://github.com/rusel95/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/rusel95/ios-agent-skills/swift-concurrency)<a href="https://agentmods.dev/skills/rusel95/ios-agent-skills/swift-concurrency"><img src="https://agentmods.dev/badge/skills/rusel95/ios-agent-skills/swift-concurrency/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/rusel95/ios-agent-skills/swift-concurrency"><img src="https://agentmods.dev/badge/skills/rusel95/ios-agent-skills/swift-concurrency.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 | $0.00170 | $0.03537 |
| Opus 5.5 | $0.00068 | $0.01415 |
| Sonnet 5.5 | $0.00034 | $0.00707 |
| Haiku 4.5 | $0.00017 | $0.00354 |
Grade A, and why
swift-concurrency 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 1mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Concurrency
Enterprise-grade skill for Swift Concurrency crash prevention, strict concurrency migration, and Swift 6.2 readiness. Opinionated: prescribes structured concurrency over unstructured, actors for shared mutable state, @MainActor for UI isolation, Mutex for synchronous critical sections, compile-time isolation over runtime hops, and withCheckedContinuation over withUnsafeContinuation. Every rule in this skill has broken a real production app.
Concurrency Layers
Application Layer -> Structured concurrency: TaskGroup, async let, .task modifier
Actor Layer -> actor for shared mutable state, @MainActor for UI state
Async/Await Layer -> Cooperative, non-blocking async functions on the cooperative pool
Sendable Layer -> Compile-time data-race safety at isolation boundary crossings
Compiler Layer -> SWIFT_STRICT_CONCURRENCY=complete, Swift 6 language mode, TSan
Quick Decision Trees
"What isolation does this type need?"
Does this type own mutable state shared across concurrency domains?
+-- YES -> Does it need to update UI?
| +-- YES -> @MainActor class/struct
| +-- NO -> Is the state complex or involves await points?
| +-- YES -> actor
| +-- NO -> Mutex<State> (Swift 6+, iOS 18+) or NSLock wrapper
+-- NO -> Is it a value type with only Sendable stored properties?
+-- YES -> Implicitly Sendable (internal types only; public needs explicit conformance)
+-- NO -> Can it be redesigned as a value type?
+-- YES -> Refactor to struct/enum
+-- NO -> Keep non-Sendable, contain within single isolation domain
"async let vs TaskGroup vs Task {}?"
How many concurrent operations?
+-- Known at compile time (2-5) -> async let (simplest, heterogeneous return types OK)
+-- Dynamic count (N items) -> TaskGroup
| +-- Need results?
| | +-- YES -> withThrowingTaskGroup (iterate with for await)
| | +-- NO -> withDiscardingTaskGroup (no result accumulation leak)
| +-- Unbounded input? -> Throttle: limit addTask to activeProcessorCount
+-- Fire-and-forget from sync context?
+-- Need caller's isolation -> Task { } (inherits actor context)
+-- Need background, no isolation -> Task.detached { }
WARNING: detached strips priority, task-locals, cancellation propagation. Rarely correct.
What ships with it
18 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.
- README.md 7.0 KB
- references/actor-isolation.md 9.4 KB
- references/advanced-patterns.md 12 KB
- references/asyncstream-memory.md 7.7 KB
- references/cancellation-patterns.md 4.9 KB
- references/compiler-flags-ci.md 6.8 KB
- references/core-data-concurrency.md 5.1 KB
- references/crash-patterns.md 11 KB
- references/diagnostics-fix-mapping.md 3.7 KB
- references/memory-retain-cycles.md 4.3 KB
- references/migration-strategy.md 8.5 KB
- references/refactoring-workflow.md 8.2 KB
- references/rules.md 4.7 KB
- references/security-concurrency.md 9.0 KB
- references/sendable-transfer.md 6.7 KB
- references/swift-6-2-changes.md 10 KB
- references/testing-async.md 5.4 KB
- references/testing-debugging.md 10 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.
- 1mo ago First seen · 202 lines · 170 tokens per session scan A 6be6625aaf6a
swift-concurrency is a skill published in the GitHub repository rusel95/ios-agent-skills (13 stars, last pushed 14d ago), licensed MIT. It adds 170 tokens to every session and 3,537 once invoked, about $0.0007 per session on Opus 5.5. 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…
android-development
Android development guidelines for Kotlin with clean architecture, MVI pattern, Material Design, and best practices for building robust mobile applications.
flutter
Expert in Flutter and Dart development with clean architecture and state management.
swiftui-max
Expert SwiftUI guidance for building UI on iOS, iPadOS, macOS, watchOS, tvOS, and visionOS. Use whenever writing, reviewing, refactoring, or debugging ANY SwiftUI code — views, view modifiers, layout, navigation (NavigationStack/SplitView, deep links), lists and scrolling, animation and transitions, state management…
apple-dev-conductor
Orchestrator for the swift-tothemax plugin — routes any Apple-platform development task (building an iOS/macOS app, adding a feature, preparing a release, fixing a rejection) to the right combination of skills in the correct order. Use this skill FIRST whenever a task spans more than one facet of Apple development …
swift
Swift programming patterns for iOS and macOS.