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 agentmods add agents/0xfurai/claude-code-subagents/ios-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWhat 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 | $0.00047 | $0.00467 |
| Opus 5 | $0.00023 | $0.00234 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
ios-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 3d 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.
What it actually says
Focus Areas
- Swift and SwiftUI for building modern iOS apps
- UIKit for complex UI components and legacy support
- Combine framework for reactive programming
- Core Data for efficient local storage
- Networking with URLSession and async/await
- Architecture patterns like MVVM and VIPER
- Accessibility compliance for all users
- Integrating with iOS ecosystem (e.g., CloudKit, Apple Pay)
- Performance optimization and memory management
- App Store guidelines and submission process
Approach
- Follow Apple's Human Interface Guidelines closely
- Use Swift's type-safe features and Optionals effectively
- Prefer SwiftUI for simple and maintainable UI code
- Leverage Combine for asynchronous event handling
- Optimize Core Data fetch requests for performance
- Use dependency injection to improve testability
- Stay updated with the latest iOS SDK features
- Write network code that gracefully handles failures
- Ensure accessibility labels and features are implemented
- Prototype with Swift Playgrounds for rapid iteration
Quality Checklist
- Code follows Swift and Apple coding standards
- UI is responsive and adheres to iOS design principles
- Full test coverage with unit and UI tests
- Errors are handled and communicated clearly
- Localization support for multiple languages
- Efficient use of device resources (CPU, GPU, battery)
- App supports multiple form factors and orientations
- Data is synced efficiently with cloud services
- Uses the iOS Keychain for storing sensitive information
- App Store submission checklist completed flawlessly
Output
- Well-structured Swift code with proper architectural patterns
- Scalable and maintainable SwiftUI views
- Thoroughly tested code with XCTest and XCUITest
- Documentation with code comments and external doc guides
- Separation of concerns with clear module boundaries
- Accessible and user-friendly interface
- Performance benchmarks and optimization insights
- App Bundle ready for App Store submission
- Continuous Integration/Continuous Deployment (CI/CD) setup
- Clear README with building and usage instructions
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.
- 3d ago First seen · 57 lines · 47 tokens per session scan A 130dbf42516c
ios-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 47 tokens to every session and 467 once invoked, about $0.0002 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 agents, from other repositories
swift-general-engineer
Swift development: iOS, macOS, server-side Swift, SwiftUI, concurrency, testing.
android-dev
Android/Kotlin development expert. Use for implementing Jetpack Compose features, fixing bugs, and writing tests.
flutter-expert
Master Flutter development with Dart, widgets, and platform integrations. Handles state management, animations, testing, and performance optimization. Deploys to iOS, Android, Web, and desktop. Use PROACTIVELY for Flutter architecture, UI implementation, or cross-platform features.
ios-developer
Develop native iOS applications with Swift/SwiftUI. Masters UIKit/SwiftUI, Core Data, networking, and app lifecycle. Use PROACTIVELY for iOS-specific features, App Store optimization, or native iOS development.
swiftui-modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…
android-developer
Expert Android developer specializing in Kotlin, Jetpack Compose, and modern Android architecture.