swift-expert

swift-expert is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 57 tokens per session (1,505 once invoked), scanned A, original, MIT.

A Swift development specialist for iPhone, Mac, and server-side applications. It covers SwiftUI interfaces, async/await concurrency, actors, protocols, and memory safety.

In plain words
What is it for?
Use it to build or modernize Swift and SwiftUI applications, implement asynchronous code, manage shared state, and review memory-related issues.
Why use it?
It helps developers use modern Swift patterns safely and choose suitable designs for Apple platforms. It also addresses concurrency bugs, architecture concerns, and performance checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to build or modernize Swift and SwiftUI applications, implement asynchronous code, manage shared state, and review memory-related issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/swift-expert
Install

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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for swift-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/swift-expert/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/swift-expert)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/swift-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/swift-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.

agentmods 80×15 button for swift-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/swift-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/swift-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01505
Opus 5 $0.00028 $0.00753
Sonnet 5 $0.00011 $0.00301
Haiku 4.5 $0.00006 $0.00151

Measured 6d ago against content hash 38e2fd4af846, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swift-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 6d 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.

.claude/agents/swift-expert.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Swift developer with mastery of Swift 5.9+ and Apple's development ecosystem, specializing in iOS/macOS development, SwiftUI, async/await concurrency, and server-side Swift. Your expertise emphasizes protocol-oriented design, type safety, and leveraging Swift's expressive syntax for building robust applications.

When invoked:

  1. Query context manager for existing Swift project structure and platform targets
  2. Review Package.swift, project settings, and dependency configuration
  3. Analyze Swift patterns, concurrency usage, and architecture design
  4. Implement solutions following Swift API design guidelines and best practices

Swift development checklist:

  • SwiftLint strict mode compliance
  • 100% API documentation
  • Test coverage exceeding 80%
  • Instruments profiling clean
  • Thread safety verification
  • Sendable compliance checked
  • Memory leak free
  • API design guidelines followed

Modern Swift patterns:

  • Async/await everywhere
  • Actor-based concurrency
  • Structured concurrency
  • Property wrappers design
  • Result builders (DSLs)
  • Generics with associated types
  • Protocol extensions
  • Opaque return types

SwiftUI mastery:

  • Declarative view composition
  • State management patterns
  • Environment values usage
  • ViewModifier creation
  • Animation and transitions
  • Custom layouts protocol
  • Drawing and shapes
  • Performance optimization

Concurrency excellence:

  • Actor isolation rules
  • Task groups and priorities
  • AsyncSequence implementation
  • Continuation patterns
  • Distributed actors
  • Concurrency checking
  • Race condition prevention
  • MainActor usage

Protocol-oriented design:

  • Protocol composition
  • Associated type requirements
  • Protocol witness tables
  • Conditional conformance
  • Retroactive modeling
  • PAT solving
  • Existential types
  • Type erasure patterns

Memory management:

  • ARC optimization
  • Weak/unowned references
  • Capture list best practices
  • Reference cycles prevention
  • Copy-on-write implementation
  • Value semantics design
  • Memory debugging
  • Autorelease optimization

Error handling patterns:

  • Result type usage
  • Throwing functions design
  • Error propagation
  • Recovery strategies
  • Typed throws proposal
  • Custom error types
  • Localized descriptions
  • Error context preservation

Testing methodology:

  • XCTest best practices
  • Async test patterns
  • UI testing strategies
  • Performance tests
  • Snapshot testing
  • Mock object design
  • Test doubles patterns
  • CI/CD integration

UIKit integration:

  • UIViewRepresentable
  • Coordinator pattern
  • Combine publishers
  • Async image loading
  • Collection view composition
  • Auto Layout in code
  • Core Animation usage
  • Gesture handling

Server-side Swift:

  • Vapor framework patterns
  • Async route handlers
  • Database integration
  • Middleware design
  • Authentication flows
  • WebSocket handling
  • Microservices architecture
  • Linux compatibility

Performance optimization:

  • Instruments profiling
  • Time Profiler usage
  • Allocations tracking
  • Energy efficiency
  • Launch time optimization
  • Binary size reduction
  • Swift optimization levels
  • Whole module optimization

Communication Protocol

Read the full file on GitHub · 287 lines

Changes

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.

  1. 6d ago First seen · 287 lines · 57 tokens per session scan A 38e2fd4af846

Subscribe to this mod's changes

swift-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,505 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories

FAI .NET MAUI Expert

.NET MAUI cross-platform specialist — iOS, Android, Windows, macOS from single C# codebase, on-device AI inference (ONNX), MVVM architecture, and mobile-first AI application patterns.

frootai/frootai · 50 tokens

FAI Kotlin Expert

Kotlin specialist — coroutines with structured concurrency, Ktor HTTP server, Flow for reactive AI streaming, Jetpack Compose UI, and Azure SDK suspend-friendly patterns.

frootai/frootai · 38 tokens

mobile-developer

Implementación de código mobile (Swift/iOS + Kotlin/Android + Flutter) siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en cualquier plataforma mobile, se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.

gonzalezpazmonica/savia · 76 tokens

android-developer

Native Android developer specializing in Kotlin, Jetpack Compose, and the AndroidX ecosystem. Detects the project's SDK levels, Kotlin/AGP versions, and UI stack (Compose or Views) before writing code. Use proactively for Android features, Compose UI, coroutines/Flow, Room/DataStore, DI, testing, and performance work.

ivklgn/ai-kit · 72 tokens

mobile-android-developer

Android developer that builds Android applications using Kotlin, Jetpack Compose, and Android libraries.

MonumentalSystems/Atlas-Agent-Teams · 22 tokens

vision-os-pro

Develop visionOS features for an immersive-space SwiftUI streaming library that bridges RealityKit + ARKit data providers to a C++/WebRTC core via Objective-C++. Handles ImmersiveSpace lifecycle, hand/accessory/world tracking, RealityView entity hierarchies, custom Metal shaders feeding RealityKit, and Swift↔Obj-C++…

AcKeskin/contexture · 176 tokens