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 nimadorostkar/Claude-Skills-collection --skill swiftgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/swift)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/swift"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/swift/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/nimadorostkar/claude-skills-collection/swift"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/swift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.00899 |
| Opus 5.5 | $0.00039 | $0.00360 |
| Sonnet 5.5 | $0.00019 | $0.00180 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
swift 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 16d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift
Purpose
Write Swift that leans on value semantics and the concurrency model rather than fighting them: structs by default, actors for shared mutable state, and no force-unwrapping.
When to Use
- Writing Swift for Apple platforms or server-side Swift.
- Migrating callback or Combine code to async/await.
- Resolving data-race warnings under strict concurrency checking.
- Designing SwiftUI state and view models.
- Diagnosing retain cycles and memory growth.
Capabilities
- Value vs reference semantics and copy-on-write.
- Optional handling:
guard let, optional chaining,Resulttypes. - Protocol-oriented design with associated types and generics.
- Structured concurrency:
async let, task groups, actors,Sendable. - SwiftUI:
@State,@Observable, and unidirectional data flow.
Inputs
- Source target, Swift version, minimum deployment target.
- Concurrency checking level (minimal, targeted, complete).
Outputs
- Code free of force-unwraps and implicit unwrapped optionals.
- Concurrency that compiles cleanly under strict checking.
- View models with a single source of truth.
Workflow
- Prefer structs — Reach for a class only when identity or shared mutation is required.
- Eliminate optionals early — Unwrap once at the boundary with
guard; the rest of the function works with non-optionals. - Isolate mutable state — Any shared mutable state becomes an actor or is confined to the main actor.
- Model async explicitly — Replace completion handlers with
asyncfunctions; use task groups for concurrency. - Gate — Build with strict concurrency checking and treat warnings as errors.
Best Practices
!is a crash waiting for a user to find it. The only acceptable uses are IBOutlets and genuinely proven invariants with a comment.- Capture lists (
[weak self]) on every escaping closure that capturesselfin a class. - Mark types
Sendabledeliberately; suppressing the warning with@unchecked Sendablerequires a documented reason. - SwiftUI views are cheap and disposable — put logic in the model, not the view body.
- Prefer
async letfor a fixed set of concurrent calls; useTaskGroupwhen the count is dynamic. - Long-running work never runs on the main actor.
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.
- 16d ago Changed · +54 tokens per session e7fe3fbbb2b1
- 1mo ago First seen · 93 lines · 43 tokens per session scan A 739b17505aa3
swift is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (33 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 899 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
neo-swift-ui
Use this skill when building, debugging, refactoring, or reviewing SwiftUI apps or views for iOS 16+ and related Apple platforms. Trigger for NavigationStack, Observation/state flow, view composition, previews, performance, accessibility, and SwiftUI architecture.
neo-swift
Use this skill when writing, reviewing, debugging, or modernizing Swift code for iOS, macOS, server-side Swift, or shared packages. Trigger for Swift 5+ language features, structured concurrency, memory safety, protocols/generics, SwiftUI integration, and performance-sensitive code.
wear-compose-m3
Guidance for Wear OS Compose Material3 (Wear Compose Material 3 / Wear Compose Material3) watch and wearable apps. Covers creating, updating, and migrating projects (Material 2.5 and Horologist migration) using androidx.wear.compose.material3, androidx.wear.compose.foundation, and androidx.wear.compose.navigation3…
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.…
swift-expert
Builds iOS/macOS/watchOS/tvOS applications, implements SwiftUI views and state management, designs protocol-oriented architectures, handles async/await concurrency, implements actors for thread safety, and debugs Swift-specific issues. Use when building iOS/macOS applications with Swift 5.9+, SwiftUI, or async/await…
ink-custom-brush-builder
Creates custom BrushFamily definitions for an Android app using Jetpack Ink (androidx.ink 1.1.0-alpha03 and higher). Use this skill when configuring custom BrushTip shapes, adding pressure, tilt, speed, or noise sensitivity using BrushBehavior node graphs, creating multi-coat layered brushes, applying tiling or…