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 skills/dev869/swift-tothemax/apple-dev-conductornpx skills add Dev869/swift-tothemax --skill apple-dev-conductorgit 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/apple-dev-conductor)<a href="https://agentmods.dev/skills/dev869/swift-tothemax/apple-dev-conductor"><img src="https://agentmods.dev/badge/skills/dev869/swift-tothemax/apple-dev-conductor.svg" alt="Measured on agentmods" 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 | $0.00156 | $0.01476 |
| Opus 5 | $0.00078 | $0.00738 |
| Sonnet 5 | $0.00031 | $0.00295 |
| Haiku 4.5 | $0.00016 | $0.00148 |
Grade A, and why
apple-dev-conductor 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Dev Conductor
You are orchestrating a suite of skills that each own one facet of Apple-platform development. Your job: decompose the task into facets, invoke the right skills in the right order, and keep their outputs consistent.
The suite (this plugin)
| Skill | Owns | Typical trigger |
|---|---|---|
swift-language |
Swift 6.x language, concurrency, performance, SwiftPM, interop, testing | any Swift code |
swiftui-max |
SwiftUI implementation: state, layout, animation, platform integration | building UI |
apple-hig-ux |
Design judgment: HIG, platform idioms, accessibility, "feels native" | designing screens/flows, UX review |
app-review-max |
Passing App Review: rejection playbook, QC checklist, monetization compliance | submission, rejection, IAP rules |
apple-legal-max |
Legal & privacy: manifests, nutrition labels, ATT, GDPR/COPPA/DMA, documents | privacy/legal anything |
apple-release-ops |
Shipping mechanics: signing, TestFlight, App Store Connect, CI/CD | build/upload/release |
ui-crawler-max |
Autonomous UI crawl: explore every screen, capture errors/crashes with repro steps, Haiku data labeling | "test the app", QA sweep, "find crashes" |
Lifecycle routing
Work through stages in order; skip stages the task doesn't touch. At each stage read the named skill's SKILL.md and follow it.
- Shape — what are we building? →
apple-hig-ux(platform idioms, navigation pattern, screen patterns). - Architect & build —
swift-language(types, concurrency, data flow) +swiftui-max(views, state). These two always load together for app code: language owns everything below the view layer. - Feature compliance gates (do EARLY, not at submission):
- Collects data / has accounts / tracking / kids / subscriptions? →
apple-legal-max(privacy manifest, labels, required documents) andapp-review-max→references/monetization-compliance.mdfor anything paid. - Account creation ⇒ account deletion (5.1.1(v)); tracking ⇒ ATT; these are cheaper to design in than retrofit.
- Collects data / has accounts / tracking / kids / subscriptions? →
- Quality pass —
apple-hig-ux→references/accessibility.mdaudit;swift-languagereview checklist; tests perswift-language→references/testing.md; then aui-crawler-maxsweep — crawl every screen, harvest console errors/crashes/unlabeled controls, and feed the findings back toswiftui-max(implementation),apple-hig-ux(design/accessibility), orswift-language(logic) for fixes. - Ship —
apple-release-ops(signing, TestFlight, CI) thenapp-review-max→references/submission-checklist.mdas the final gate. - Rejected / incident —
app-review-max→references/rejection-playbook.md; crash spikes →apple-release-ops.
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.
- 5d ago First seen · 68 lines · 156 tokens per session scan A e9849b5dfce2
apple-dev-conductor is a skill published in the GitHub repository Dev869/swift-tothemax (7 stars, last pushed 2mo ago), licensed MIT. It adds 156 tokens to every session and 1,476 once invoked, about $0.0008 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.