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 patrickserrano/lacquer --skill watchos-developmentgit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/patrickserrano/lacquer/watchos-development)<a href="https://agentmods.dev/skills/patrickserrano/lacquer/watchos-development"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/watchos-development/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/patrickserrano/lacquer/watchos-development"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/watchos-development.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 | $0.00071 | $0.01564 |
| Opus 5.5 | $0.00028 | $0.00626 |
| Sonnet 5.5 | $0.00014 | $0.00313 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
watchos-development 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
watchOS Development
Guidance for building watchOS apps that behave the way the platform expects: independent by default, SwiftUI-first, glanceable, and resilient to a paired iPhone that may not be nearby.
Agent behavior contract (follow these rules)
- Determine the project's shape before proposing changes: watch-only, paired companion, or independent+companion. Default recommendation for new work is independent + companion — it's the only shape that degrades gracefully on Family Setup watches and unpaired watches.
- Never let Watch Connectivity become the primary data path. It is an opportunistic optimization on top of a network/CloudKit fetch, not a substitute for one — see
references/watch-connectivity.md. - Default new app entry points to the SwiftUI
Appprotocol (@main,WindowGroup,NavigationStack) — seereferences/platform-basics.mdfor entry-point structure andreferences/design-for-watchos.mdfor how these primitives handle watchOS-specific navigation. Only add aWKApplicationDelegatevia@WKApplicationDelegateAdaptorfor the specific callbacks SwiftUI doesn't expose (workout recovery, Now Playing, extended runtime, remote-notification registration) — never as a precaution. - Route all networking through
URLSession. Low-level networking (NWConnection, raw sockets,URLSessionStreamTask/WebSocketTask) is blocked by the OS on watchOS except for audio-streaming, VoIP+CallKit, and tvOS-pairing apps — seereferences/background-and-networking.md. - Every
WKRefreshBackgroundTask(includingWKWatchConnectivityRefreshBackgroundTaskandWKURLSessionRefreshBackgroundTask) must reachsetTaskCompletedWithSnapshot(_:)exactly once. Missing this drains the background budget and produces a delayedSIGKILLthat looks unrelated to its cause. - When migrating ClockKit complications to WidgetKit, insist on migrating every complication in the same release. The instant one WidgetKit complication is offered, the system stops calling ClockKit entirely — a partial migration silently breaks the rest on every user's device.
- For SwiftUI content, only cover what's genuinely different on watchOS (navigation primitives, toolbar placement, Always On, containerBackground). General SwiftUI state management, layout, and animation belong to the
swiftui-expert-skillandswiftui-liquid-glassskills — don't re-explain those here. - For workouts and HealthKit specifics (HKWorkoutSession, HKLiveWorkoutBuilder, recovery), defer to the
healthkitskill; this skill only covers how workout data affects Smart Stack suggestions.
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.
- LICENSE 1.4 KB
- references/background-and-networking.md 12 KB
- references/controls-and-live-activities.md 11 KB
- references/design-for-watchos.md 10.0 KB
- references/modernization.md 10 KB
- references/platform-basics.md 8.8 KB
- references/smart-stack-and-complications.md 9.3 KB
- references/watch-connectivity.md 11 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.
- 1mo ago First seen · 67 lines · 71 tokens per session scan A 203eb6871e9c
watchos-development is a skill published in the GitHub repository patrickserrano/lacquer (5 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,564 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 2026-09-03.
Other skills, from other repositories
sweetpad
Build, run, and test Xcode and Swift Package apps from the terminal with the sweetpad CLI ("xcodebuild for humans"). Use when the user wants to compile an iOS/macOS/Swift app, run it on a simulator or device, read build errors, run tests, or inspect resolved build settings from the command line — with agent-safe…
build-feature
Build an iOS feature using ShipSwift components. Use when the user says "build", "create", "add a feature", or describes an iOS feature they want to implement.
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
ios-slim-bindings
Create iOS slim bindings for MAUI. USE FOR: slim iOS binding, Native Library Interop, Swift/Objective-C wrappers, XcodeGen project.yml, Podfile, CocoaPods static linking, BUILDLIBRARYFORDISTRIBUTION, XcodeProject MSBuild, @objc/[Export] selector crashes, async completion handlers. DO NOT USE FOR: Android bindings…
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.