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 SwiftyJourney/ios-architecture-expert-skill --skill ios-architecture-expertgit clone --depth 1 https://github.com/SwiftyJourney/ios-architecture-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/swiftyjourney/ios-architecture-expert-skill/ios-architecture-expert)<a href="https://agentmods.dev/skills/swiftyjourney/ios-architecture-expert-skill/ios-architecture-expert"><img src="https://agentmods.dev/badge/skills/swiftyjourney/ios-architecture-expert-skill/ios-architecture-expert/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/swiftyjourney/ios-architecture-expert-skill/ios-architecture-expert"><img src="https://agentmods.dev/badge/skills/swiftyjourney/ios-architecture-expert-skill/ios-architecture-expert.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 | $0.00232 | $0.04862 |
| Opus 5 | $0.00116 | $0.02431 |
| Sonnet 5 | $0.00046 | $0.00972 |
| Haiku 4.5 | $0.00023 | $0.00486 |
Grade A, and why
ios-architecture-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 12d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Architecture Expert — Clean Modular Architecture
Agent Behavior Contract
When this skill is active, follow these rules strictly:
- Feature modules have zero UIKit/SwiftUI imports — only Foundation. Domain models, use cases, presenters, and API/cache logic never depend on a UI framework.
- Define a boundary at every layer transition — protocol or closure. A layer never references a concrete type from another layer. Use a protocol when there are genuinely multiple strategies (
FeedStore,HTTPClient,ResourceView,FeedCache); use a plain composed closure (() async throws -> Resource) when there is one — see rule 12. - Domain models are value types —
struct,Hashable,Sendable. No classes for models. - Presentation logic is framework-agnostic — presenters output view models (structs). No
UIImage,UIColor, or SwiftUI types in the presentation layer. - All dependency wiring happens in the Composition Root — the app target (or a dedicated
CompositionRootmodule). Feature modules never create their own dependencies. - Tests drive the design — one test class per use case, named by behavior (
CacheFeedUseCaseTests, notLocalFeedLoaderTests). UsemakeSUT()factory in every test class. - Test only the public API — no
@testable importoutside the Composition Root. Test targets use a plainimport Feed; a behavior that can't be observed publicly is a missing public seam (a boundary, a return value, an injected collaborator), never a reason to widen the test's access. This is deliberately stricter than the source codebase, which uses@testablein a handful of places — the full argument and the Composition Root exception live intestability-and-seams.md. - Use SPM multi-target packages for module separation —
Feed(Foundation),FeediOS(UIKit),App(composition). - Prefer async/await over closures/Combine for async operations. Use
Task.immediatefor synchronous-first execution in adapters where the deployment target allows it (iOS 26+; plainTask+ observable-state tests is the documented fallback — seeconcurrency-at-boundaries.md). - Match the project's existing test framework; default to Swift Testing for greenfield suites. For test doubles, test design, deterministic async testing, Swift Testing syntax and XCTest migration, defer to the
swift-testing-expertskill. This skill keeps only the places where a testing decision is a design decision — seetestability-and-seams.md. Two things that bite regardless:trackForMemoryLeaks/addTeardownBlockis XCTest-only (the Swift Testing equivalent is a test-scoping trait, ST-0007), and Swift Testing runs tests in parallel by default, so suites sharing a store URL or on-disk artifacts need.serialized. - Mark shared mutable state with
@MainActor— presenters, adapters, view controllers, and composition code run on the main actor. - Do not add a protocol boundary that has only one implementation and no second strategy in sight — compose a closure in the Composition Root instead. Boundaries exist to select between strategies.
What ships with it
12 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/adapters-and-proxies.md 24 KB
- references/architecture-layers.md 23 KB
- references/composition-root.md 29 KB
- references/concurrency-at-boundaries.md 26 KB
- references/dependency-management.md 15 KB
- references/design-principles.md 26 KB
- references/feature-implementation-workflow.md 19 KB
- references/infrastructure-and-networking.md 16 KB
- references/presentation-patterns.md 24 KB
- references/spm-project-structure.md 26 KB
- references/swiftui-composition.md 15 KB
- references/testability-and-seams.md 19 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.
- 12d ago First seen · 225 lines · 232 tokens per session scan A 9534c5a52135
ios-architecture-expert is a skill published in the GitHub repository SwiftyJourney/ios-architecture-expert-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 232 tokens to every session and 4,862 once invoked, about $0.0012 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
frontend-architecture
Component architecture, design patterns, state management strategies, module systems, build tools, and scalable application structure.
swift-protocol-di-testing
Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.
svc-mobile-android
Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.
modular-skills
Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
kotlin-patterns
Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.