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 markdavidgan/apple-dev-skills --skill apple-devgit clone --depth 1 https://github.com/markdavidgan/apple-dev-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/markdavidgan/apple-dev-skills/apple-dev)<a href="https://agentmods.dev/skills/markdavidgan/apple-dev-skills/apple-dev"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/apple-dev/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/markdavidgan/apple-dev-skills/apple-dev"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/apple-dev.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 | $0.00031 | $0.00147 |
| Opus 5.5 | $0.00012 | $0.00059 |
| Sonnet 5.5 | $0.00006 | $0.00029 |
| Haiku 4.5 | $0.00003 | $0.00015 |
Grade A, and why
apple-dev 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
Apple Dev Skills — Plugin Host
This directory hosts the Kimi-specific apple-dev plugin tools.
pattern-check— Run mechanical Swift 6 / SwiftUI / SwiftData / entitlements / safety auditapi-lookup— Query iOS 26 API signatures and anti-hallucination reference
For the full skill index, see reference/all-skills.md.
Load a specific skill by invoking its name, e.g. /skill:swift6-concurrency.
What ships with it
60 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.
- commands/apple-check.md 222 B
- commands/apple-cleanup.md 367 B
- commands/apple-polish.md 444 B
- commands/apple-review.md 330 B
- commands/arch-diagram.md 264 B
- commands/aso-audit.md 459 B
- commands/check-build.md 255 B
- commands/complete-feature.md 220 B
- commands/design-handoff.md 795 B
- commands/fit-check.md 577 B
- commands/icon-composer.md 761 B
- commands/marketing-context.md 518 B
- commands/merge-check.md 300 B
- commands/overlay-sync.md 1.1 KB
- commands/perf-audit.md 564 B
- commands/preflight.md 570 B
- commands/prepare-submission.md 283 B
- commands/privacy-check.md 513 B
- commands/regression-test.md 321 B
- commands/rejection-recovery.md 501 B
- commands/review-triage.md 513 B
- commands/security-check.md 536 B
- commands/setup-asc.md 4.4 KB
- commands/swift6-fix.md 289 B
- commands/write-spec.md 495 B
- plugin.json 1.7 KB
- reference/all-skills.md 30 KB
- reference/CHANGELOG.md 6.1 KB
- reference/essentials/app-intents.md 9.1 KB
- reference/essentials/avfoundation.md 12 KB
- reference/essentials/foundation-models.md 21 KB
- reference/essentials/macos.md 11 KB
- reference/essentials/network.md 13 KB
- reference/essentials/speech.md 9.2 KB
- reference/essentials/swift6.md 11 KB
- reference/essentials/swiftdata.md 11 KB
- reference/essentials/swiftui.md 12 KB
- reference/essentials/videotoolbox.md 10 KB
- reference/essentials/vision.md 11 KB
- reference/essentials/watchos.md 5.4 KB
- reference/essentials/widgets.md 9.2 KB
- reference/guides/expert-swift6.md 29 KB
- reference/intel/community-foundation-models.md 20 KB
- reference/intel/community-naturallanguage.md 5.5 KB
- reference/intel/community-speech.md 17 KB
- reference/intel/community-swift6.md 24 KB
- reference/intel/community-swiftui.md 2.7 KB
- reference/reference/app-intents-reference.md 42 KB
- reference/reference/apple-guides.md 79 KB
- reference/reference/avfoundation-reference.md 46 KB
- reference/reference/crash-cheat-sheet.md 10 KB
- reference/reference/foundation-models-reference.md 46 KB
- reference/reference/network-reference.md 94 KB
- reference/reference/speech-reference.md 50 KB
- reference/reference/swift6-reference.md 43 KB
- reference/reference/swiftdata-reference.md 57 KB
- reference/reference/swiftui-reference.md 50 KB
- reference/reference/videotoolbox-reference.md 68 KB
- reference/reference/vision-reference.md 74 KB
- reference/reference/widgets-reference.md 52 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 · 16 lines · 31 tokens per session scan A 3df3f02917cb
apple-dev is a skill published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 147 once invoked, about $0.0001 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
react-native-native-modules
Writing native code for React Native's New Architecture — choosing between Turbo Modules, Fabric components, Expo Modules and Nitro, Codegen specs, Kotlin and Objective-C++/Swift implementations, events, threading, and scaffolding/publishing libraries with create-react-native-library.
asc-revenuecat-catalog-sync
Reconcile App Store Connect subscriptions and in-app purchases with RevenueCat products, entitlements, offerings, and packages using asc and RevenueCat MCP. Use when setting up or syncing subscription catalogs across ASC and RevenueCat.
asc-localize-metadata
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.
asc-metadata-sync
Sync, validate, and apply App Store metadata and store assets with asc. Use when updating localizations, keywords, App Clip or preview assets, Asset Library media and placements, or migrating legacy fastlane metadata.
asc-shots-pipeline
Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…
asc-release-flow
Orchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review. Use when the user wants to prepare or execute a release. Keep Game Center item preparation in this skill; route other readiness failures, stuck submissions, cancellation, and…