swiftui-expert

swiftui-expert is a skill for Claude Code from johnkozaris/jko-claude-plugins. It costs 133 tokens per session (982 once invoked), scanned A, original, MIT.

A guide for making design and architecture decisions in SwiftUI, Apple's framework for building app interfaces with Swift. It covers state ownership, navigation, concurrency, storage, accessibility, performance, and platform behavior.

In plain words
What is it for?
It is for reviewing or designing SwiftUI screens and features, including shared state, view identity, navigation, persistence, deep links, offline behavior, and testing boundaries.
Why use it?
SwiftUI decisions often depend on the app's deployment targets, existing state flow, and lifecycle needs; this guide examines those details before recommending an approach.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the swiftui plugin — 1 skill shipped together

Good fit It is for reviewing or designing SwiftUI screens and features, including shared state, view identity, navigation, persistence, deep links, offline behavior, and testing boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnkozaris/jko-claude-plugins/swiftui-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.

Any agent
npx skills add johnkozaris/jko-claude-plugins --skill swiftui-expert
Clone the repo
git clone --depth 1 https://github.com/johnkozaris/jko-claude-plugins

Made for: Claude Code.

Or install swiftui, the plugin that ships this one along with the rest of its 1 skill.

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 swiftui-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/swiftui-expert/github.svg)](https://agentmods.dev/skills/johnkozaris/jko-claude-plugins/swiftui-expert)
Your own site
<a href="https://agentmods.dev/skills/johnkozaris/jko-claude-plugins/swiftui-expert"><img src="https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/swiftui-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 swiftui-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnkozaris/jko-claude-plugins/swiftui-expert"><img src="https://agentmods.dev/badge/skills/johnkozaris/jko-claude-plugins/swiftui-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 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 $0.00133 $0.00982
Opus 5 $0.00067 $0.00491
Sonnet 5 $0.00027 $0.00196
Haiku 4.5 $0.00013 $0.00098

Measured 9d ago against content hash fada4f44628a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swiftui-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 9d 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.

plugins/swiftui/skills/swiftui-expert/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftUI Expert

Inspect the project before applying a default. Read its deployment targets, Swift language mode, existing state patterns, platform targets, dependencies, and nearby code. Look up current Apple documentation before making a load-bearing claim about API behavior or availability.

If a missing target, isolation setting, ownership fact, deep-link/restoration need, sync topology, offline behavior, or minimum-OS decision would materially change the answer, ask one focused question or present conditional recommendations.

Opinions worth carrying

  • Use SwiftUI's data flow directly by default. Let views compose sources of truth with @State, @Environment, @Bindable, and query wrappers. Add a ViewModel when it owns real orchestration: a state machine, retries, pagination, optimistic updates, lifecycle independent of one view, or a valuable test seam. Do not introduce one merely to move properties out of a view.
  • Own shared observable state at a clear ancestor. App-wide @Observable instances normally originate in App and enter the environment. Keep ownership distinct from observation and binding extraction.
  • Model navigation as state when the product needs restoration, deep links, or independent tab histories. Prefer typed destinations and keep one navigation history per independent surface. Do not force a router into a small linear flow that gains nothing from it.
  • Treat view identity and lifecycle as correctness concerns. Work tied to a view belongs in lifecycle-aware tasks; structural changes, unstable IDs, and hidden side effects can recreate state or repeat work unexpectedly.
  • Use modern concurrency deliberately. Match recommendations to the project's Swift mode and isolation settings. App targets often benefit from main-actor defaults; reusable non-UI packages often should remain nonisolated. Treat @unchecked Sendable as a synchronization claim that must be visible in the code.
  • Respect the platform. A Mac app needs menus, keyboard behavior, windows, and AppKit bridges where SwiftUI is weak. An iOS app needs real accessibility, lifecycle, permission, privacy, and background-behavior review. Do not infer one platform's conventions from another.
  • Do not modernize for sport. Preserve coherent working patterns on older deployment targets unless the current change benefits from migration.

Read the full file on GitHub · 87 lines

Files

What ships with it

8 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.

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. 9d ago First seen · 87 lines · 133 tokens per session scan A fada4f44628a

Subscribe to this mod's changes

swiftui-expert is a skill published in the GitHub repository johnkozaris/jko-claude-plugins (11 stars, last pushed 12d ago), licensed MIT. It adds 133 tokens to every session and 982 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

swiftui-expert

This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…

mathisk2095/jko-claude-plugins · 162 tokens

build-android-binary

Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…

microsoft/power-platform-skills · 150 tokens

build-ios-binary

Compile a PAM control's iOS Obj-C/Swift module into the FLAT device-slice .framework for a .ppmplugin bundle (never an .xcframework — the wrap CI won't descend into one). Mac-only (Xcode). Builds from a throwaway staged copy so canonical ios/ and the podspec stay untouched, references React-Core headers only (React is…

microsoft/power-platform-skills · 200 tokens

dotnet-backend-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting pure .NET backend code for Kestrel-hosted services. It provides expert critique for REST endpoints, SignalR hubs, TypeScript/React client integration shape, pragmatic Rust interop, application services, AppHost-aware project…

mathisk2095/jko-claude-plugins · 181 tokens

esp32-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting C++ firmware for ESP32 and variants (ESP32-S2, S3, C3, C6, H2, P4) using ESP-IDF or PlatformIO. Provides expert critique covering FreeRTOS task design, memory management (IRAM/DRAM/PSRAM), peripheral drivers (I2C/SPI/UART/GPIO)…

mathisk2095/jko-claude-plugins · 193 tokens

python-backend-expert

This skill should be used when the user is writing, reviewing, debugging, or architecting Python backend code using Litestar or FastAPI with SQLAlchemy or Advanced Alchemy. Provides expert critique covering SOLID principles, hexagonal architecture, repository/service patterns, dependency injection, async correctness…

mathisk2095/jko-claude-plugins · 183 tokens