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 app-clipgit 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/app-clip)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/app-clip"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/app-clip/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/app-clip"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/app-clip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00045 | $0.02092 |
| Opus 5 | $0.00023 | $0.01046 |
| Sonnet 5 | $0.00009 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
app-clip 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 10d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Clip Generator
Generate production App Clip infrastructure — a lightweight version of your app invoked from NFC tags, QR codes, Safari banners, or Messages. Includes App Clip target setup, invocation URL handling, experience routing, location confirmation, and full app upgrade flow.
When This Skill Activates
Use this skill when the user:
- Asks to "add an app clip" or "create an app clip target"
- Mentions "instant app" or "lightweight app experience"
- Wants to set up "App Clip Card" metadata
- Mentions "NFC tag" invocation or "QR code" launching an app
- Asks about "app clip invocation" or "invocation URL handling"
- Wants a "lightweight app experience" for a physical location
Pre-Generation Checks
1. Project Context Detection
- Check deployment target (iOS 14+ required for App Clips, iOS 16+ recommended)
- Check Swift version (requires Swift 5.9+)
- Check for @Observable support (iOS 17+ / macOS 14+)
- Identify Xcode project structure (.xcodeproj or .xcworkspace)
2. Conflict Detection
Search for existing App Clip targets:
Glob: **/*AppClip*/*.swift, **/*Clip*/*.swift
Grep: "NSUserActivityTypeBrowsingWeb" or "AppClipExperience" or "SKOverlay"
If existing App Clip target found:
- Ask if user wants to replace or extend it
- If extending, identify which components are missing
3. Project Structure
Identify where the main app target lives and where to place the App Clip target alongside it.
Configuration Questions
Ask user via AskUserQuestion:
-
Invocation method?
- NFC tag only
- QR code only
- Safari banner (Smart App Banner)
- Messages
- All of the above — recommended
-
Primary experience?
- Order food (restaurant/cafe)
- Reserve (booking/reservation)
- Check in (event/location)
- Preview content (article/product)
-
Include location confirmation?
- Yes — verifies user is physically at the expected location (recommended for physical-world invocations)
- No — skip location verification
What ships with it
2 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.
- 10d ago First seen · 256 lines · 45 tokens per session scan A 1c0c6484cef6
app-clip is a skill published in the GitHub repository rshankras/claude-code-apple-skills (713 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,092 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.