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 rshankras/claude-code-apple-skills --skill watchosgit clone --depth 1 https://github.com/rshankras/claude-code-apple-skillsWrote 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/rshankras/claude-code-apple-skills/watchos)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/watchos"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/watchos/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/rshankras/claude-code-apple-skills/watchos"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/watchos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00039 | $0.03551 |
| Opus 5.5 | $0.00016 | $0.01420 |
| Sonnet 5.5 | $0.00008 | $0.00710 |
| Haiku 4.5 | $0.00004 | $0.00355 |
Grade A, and why
watchOS 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 2d 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 — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
watchOS Development
Comprehensive guidance for watchOS app development with SwiftUI, Watch Connectivity, and complications.
When This Skill Activates
Use this skill when the user:
- Is building a watchOS app or Watch extension
- Asks about Watch Connectivity (iPhone ↔ Watch sync)
- Needs help with complications or ClockKit
- Wants to implement watch-specific UI patterns
- Asks about WidgetKit complications or migrating from ClockKit to WidgetKit
- Wants to build watch face complications (accessoryCircular, accessoryRectangular, accessoryCorner, accessoryInline)
- Asks about HealthKit on watchOS, workout sessions, heart rate, or fitness tracking
- Needs Extended Runtime sessions for background workout tracking
- Wants to build watchOS widgets or Smart Stack widgets
- Asks about widget relevance, Smart Stack ordering, or widget suggestions
- Needs to share widgets cross-platform between iOS and watchOS
- Asks about watchOS accessibility — VoiceOver, AssistiveTouch, or Dynamic Type on the Watch
Key Principles
1. Watch-First Design
- Glanceable content - users look for seconds, not minutes
- Quick interactions - 2 seconds or less
- Essential information only - no scrolling walls of text
- Large touch targets - minimum 38pt height
2. Independent vs Companion
- Prefer independent Watch apps when possible
- Use Watch Connectivity for data sync, not as dependency
- Cache data locally for offline access
- Handle connectivity failures gracefully
3. Performance
- Minimize background work (battery)
- Use complication updates sparingly
- Prefer timeline-based content over live updates
- Keep views lightweight
watchOS Design Rules (WWDC20/23)
The Ten-Second Test
Design for roughly ten seconds of attention: "if you had ten seconds of someone's attention, which information would you surface?" Launch directly into that detail view — chosen by location, recency, or frequency — and make it so unmistakable it needs no title.
What ships with it
4 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.
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.
- 2d ago First seen · 459 lines · 39 tokens per session scan A 347376d31d4b
watchOS is a skill published in the GitHub repository rshankras/claude-code-apple-skills (864 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 3,551 once invoked, about $0.0002 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 2026-11-05.
watchOS compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| watchOSrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 39 | Claude Code |
| swift-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 76 | Claude Code |
| ios-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 64 | Claude Code |
| ios-swiftui-productJasonColapietro/ios-app-dev-skills | Skill | 9 | 2mo ago | MIT | A | 67 | Codex |
| swiftui-maxDev869/swift-tothemax | Skill | 7 | 4mo ago | MIT | A | 271 | Claude Code |
| apple-dev-conductorDev869/swift-tothemax | Skill | 7 | 4mo ago | MIT | A | 156 | Claude Code |
| kotlin-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 51 | Claude Code |