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 Abdullah4AI/apple-developer-toolkit --skill live-activitiesgit clone --depth 1 https://github.com/Abdullah4AI/apple-developer-toolkitWrote 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/abdullah4ai/apple-developer-toolkit/live-activities)<a href="https://agentmods.dev/skills/abdullah4ai/apple-developer-toolkit/live-activities"><img src="https://agentmods.dev/badge/skills/abdullah4ai/apple-developer-toolkit/live-activities/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/abdullah4ai/apple-developer-toolkit/live-activities"><img src="https://agentmods.dev/badge/skills/abdullah4ai/apple-developer-toolkit/live-activities.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 | $0.00066 | $0.00817 |
| Opus 5.5 | $0.00026 | $0.00327 |
| Sonnet 5.5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
live-activities 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 1mo 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
Live Activities
LIVE ACTIVITIES (ActivityKit + Dynamic Island): FRAMEWORK: import ActivityKit
SETUP:
- Requires separate extension target (kind: "live_activity" in plan extensions array)
- NSSupportsLiveActivities: YES is auto-configured on the main app target in project.yml
- AppGroup entitlements are auto-configured for data sharing between app and extension
ATTRIBUTES (define in Shared/ directory so both app and extension compile it): struct DeliveryAttributes: ActivityAttributes { public struct ContentState: Codable, Hashable { var status: String // Mutable: changes during the activity var progress: Double } var orderID: String // Static: set at start, cannot change }
STARTING AN ACTIVITY (in app): let attributes = DeliveryAttributes(orderID: "123") let initialState = DeliveryAttributes.ContentState(status: "Preparing", progress: 0.0) let content = ActivityContent(state: initialState, staleDate: nil) let activity = try Activity.request(attributes: attributes, content: content)
UPDATING AN ACTIVITY: let updatedState = DeliveryAttributes.ContentState(status: "On the way", progress: 0.6) let updatedContent = ActivityContent(state: updatedState, staleDate: nil) await activity.update(updatedContent)
ENDING AN ACTIVITY: await activity.end(nil, dismissalPolicy: .immediate)
LOCK SCREEN / DYNAMIC ISLAND UI (in extension): struct DeliveryLiveActivityView: View { let context: ActivityViewContext var body: some View { HStack { Text(context.state.status); ProgressView(value: context.state.progress) } } }
struct DeliveryWidget: Widget { var body: some WidgetConfiguration { ActivityConfiguration(for: DeliveryAttributes.self) { context in DeliveryLiveActivityView(context: context) // Lock Screen } dynamicIsland: { context in DynamicIsland { DynamicIslandExpandedRegion(.leading) { Text(context.state.status) } DynamicIslandExpandedRegion(.trailing) { ProgressView(value: context.state.progress) } } compactLeading: { Image(systemName: "bicycle") } compactTrailing: { Text("(Int(context.state.progress * 100))%") } minimal: { ProgressView(value: context.state.progress) } } } }
MANDATORY FILES (every live activity extension MUST have ALL of these):
- {Name}Bundle.swift — @main WidgetBundle entry point. Without this, the extension has no entry point → linker error "undefined symbol: _main" → CodeSign failure.
- LiveActivityWidget.swift — Widget struct with ActivityConfiguration(for: Attributes.self) for Lock Screen and Dynamic Island UI.
- (Optional) Intents.swift — AppIntents for interactive buttons (complete, skip, etc.).
SHARED TYPES (CRITICAL):
- ActivityAttributes struct MUST be defined in Shared/ directory (NOT in main app's Models/). Both the main app and the live activity extension compile Shared/, so the type is visible to both. Defining it only in the main app causes "Cannot find type in scope" in the extension.
SWIFT 6 CONCURRENCY:
- AppIntent static properties MUST use "static let" (not "static var"). Mutable global state violates Swift 6 concurrency rules.
- LiveActivityService (if @MainActor) → all ViewModels calling it must also be @MainActor.
PUSH-TO-START: Use APNs with activity-update payload to start activities remotely (advanced, requires server).
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.
- 1mo ago First seen · 78 lines · 66 tokens per session scan A 5bc96b3e9e9f
live-activities is a skill published in the GitHub repository Abdullah4AI/apple-developer-toolkit (11 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 817 once invoked, about $0.0003 per session on Opus 5.5. 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
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…