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 Dev869/swift-tothemax --skill swiftui-maxgit clone --depth 1 https://github.com/Dev869/swift-tothemaxWrote 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/dev869/swift-tothemax/swiftui-max)<a href="https://agentmods.dev/skills/dev869/swift-tothemax/swiftui-max"><img src="https://agentmods.dev/badge/skills/dev869/swift-tothemax/swiftui-max/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/dev869/swift-tothemax/swiftui-max"><img src="https://agentmods.dev/badge/skills/dev869/swift-tothemax/swiftui-max.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 | $0.00271 | $0.03350 |
| Opus 5 | $0.00135 | $0.01675 |
| Sonnet 5 | $0.00054 | $0.00670 |
| Haiku 4.5 | $0.00027 | $0.00335 |
Grade A, and why
swiftui-max 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI to the Max
Write SwiftUI the way a senior Apple-platforms engineer writes it in mid-2026: Observation-first, value-typed, identity-aware, and Liquid Glass-native. Prefer deleting code to adding it; most SwiftUI bugs are self-inflicted state or identity problems.
Scope split: This skill owns UI. Swift language, strict concurrency, actors/Sendable, macros, SwiftPM, and Swift Testing belong to the sibling swift-language skill — route there instead of answering language questions here (e.g. "is this Sendable", Swift 6 migration, @concurrent). SwiftUI code that contains concurrency needs both.
Give yourself eyes (mandatory for UI work)
UI built blind is the single biggest quality gap in agent-written SwiftUI. Never declare UI work done without having rendered and looked at it. The loop:
- Build for the simulator (
xcodebuild -scheme App -destination 'platform=iOS Simulator,name=iPhone 17' build) or, for isolated components, render withImageRendererfrom a scratch target. - Screenshot:
xcrun simctl io booted screenshot /tmp/screen.png— then read the image and critique it againstapple-hig-uxstandards (spacing, hierarchy, Dynamic Type, dark mode). - Repeat across the matrix that matters: light/dark, small/large Dynamic Type, smallest + largest supported device.
- Lock in what's right with snapshot tests so regressions are caught without eyes.
Full workflow (simulator CLI, PreviewHost pattern, hot reload with Inject, snapshot testing, accessibility audits): references/visual-iteration-workflow.md.
Build vs. recipe vs. library
Before hand-rolling any common component, check references/component-recipes.md (canonical implementations of the 12 hardest-to-get-right components) and references/ecosystem-libraries.md (curated, maintenance-verified third-party catalog: effects, images, markdown, dev tooling, architecture). Default order: native API → recipe from this skill → library from the vetted list. Never re-implement what Pow/Nuke/Lottie already do well; never import a library for what native does in 20 lines. For app-wide consistency (tokens, themes, reusable components), follow references/design-system-kit.md and consume tokens instead of magic numbers.
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.
- references/component-recipes.md 24 KB
- references/design-system-kit.md 13 KB
- references/ecosystem-libraries.md 15 KB
- references/layout-and-animation.md 8.9 KB
- references/performance-and-debugging.md 7.7 KB
- references/platform-integration.md 7.8 KB
- references/state-and-data-flow.md 8.0 KB
- references/visual-iteration-workflow.md 15 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.
- 8d ago First seen · 136 lines · 271 tokens per session scan A 535afbc117a7
swiftui-max is a skill published in the GitHub repository Dev869/swift-tothemax (7 stars, last pushed 2mo ago), licensed MIT. It adds 271 tokens to every session and 3,350 once invoked, about $0.0014 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
swiftui
Route SwiftUI implementation tasks to the correct Knowledge Contracts — view composition, view identity in ForEach/List, modifier order, NavigationStack/NavigationPath, NavigationSplitView, stack/spacing layout, safe area handling, lazy grids/stacks, GeometryReader pitfalls, @State/@Binding, the @Observable macro…
combine
Route Combine implementation tasks to the correct Knowledge Contracts -- the Publisher/Subscriber protocol pair, sink(receiveCompletion:receiveValue:)/sink(receiveValue:) and retaining the returned AnyCancellable; @Published/ObservableObject and the synthesized objectWillChange publisher; PassthroughSubject vs.…
foundation
Route Swift Foundation framework implementation tasks to the correct Knowledge Contracts -- date/time formatting, measurement and unit formatting, Codable encoding and custom conformance, and FileManager app sandbox directories. Use when working with DateFormatter, ISO8601DateFormatter, Date.FormatStyle, .formatted()…
generators
Code generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prompts, networking, authentication, paywalls, settings, persistence, error monitoring, CI/CD pipelines, localization, push notifications, deep linking, testing…
swift-expert
Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.
ios-expert
Expert in iOS development with SwiftUI, UIKit, Combine, and Apple ecosystem integration. Use when the user mentions mobile, Swift, SwiftUI, UIKit, Apple platforms, or Xcode, or when the task involves iOS App Architecture, SwiftUI Fundamentals, UIKit Essentials, or Combine Framework.