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 cruisediary/apple-app-review-skills --skill metadata-accuracygit clone --depth 1 https://github.com/cruisediary/apple-app-review-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/cruisediary/apple-app-review-skills/metadata-accuracy)<a href="https://agentmods.dev/skills/cruisediary/apple-app-review-skills/metadata-accuracy"><img src="https://agentmods.dev/badge/skills/cruisediary/apple-app-review-skills/metadata-accuracy/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/cruisediary/apple-app-review-skills/metadata-accuracy"><img src="https://agentmods.dev/badge/skills/cruisediary/apple-app-review-skills/metadata-accuracy.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 | $0.00039 | $0.02009 |
| Opus 5.5 | $0.00016 | $0.00804 |
| Sonnet 5.5 | $0.00008 | $0.00402 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
metadata-accuracy 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Metadata Accuracy
Purpose
Detects mismatches between features claimed in App Store metadata descriptions and features actually implemented in the codebase, enforcing Guideline 2.3.1 which prohibits misleading app descriptions.
Apple Guideline
- Primary: 2.3.1 — Performance: Accurate Metadata — App Descriptions
- Related: 2.3.10
- Reference:
references/guidelines/2-performance.md
Real-World Rejection Cases
-
Case: App description mentioned "AR features" but app had no ARKit code — rejected for misleading metadata Source: Apple Developer Forums (Guideline 2.3.1 enforcement) Root cause: App description must accurately represent actual features in the submitted build — reviewers test claimed features and will reject if they cannot find them
-
Case: App description referenced Android-only features — rejected under 2.3.10 Source: mobiloud.com/blog/avoid-app-rejected-apple Root cause: Metadata must focus on Apple platform experience only — references to other platforms mislead App Store users and violate platform-specific metadata requirements
-
Case: React Native cross-platform app displayed Android package name strings (e.g.,
com.android.vending, "Get it on Google Play") inside the onboarding flow — reviewer saw Android-specific UI text on an iOS device — rejected under 2.3.10 Source: Apple Developer Forums (multiple cross-platform developer reports) Root cause: Cross-platform apps built with React Native, Flutter, or Capacitor sometimes include Android-specific strings, icons, or navigation patterns that surface in the iOS build — reviewers flag any visible Android platform references inside the running app, not just in the App Store description
Trigger
Invoke on any iOS/macOS project before App Store submission to verify metadata accurately reflects the app's implemented features.
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 · 146 lines · 39 tokens per session scan A e8644239def8
metadata-accuracy is a skill published in the GitHub repository cruisediary/apple-app-review-skills (19 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 2,009 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 2026-09-05.
Other skills, from other repositories
cli-anything-nslogger
CLI harness for NSLogger — parse, filter, export, and monitor NSLogger log files (.rawnsloggerdata / .nsloggerdata).
benchmark
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
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.
boutique-best-practices
Best practices for using Boutique with Swift 6 concurrency, @Observable, @ObservationIgnored, Sendable conformance, testing with preview stores, and dependency injection. Use when troubleshooting Boutique issues, migrating to Swift 6, or setting up tests.
boutique-store
Create and use Boutique Store for Swift data persistence, including initialization, @Stored controllers, CRUD operations, operation chaining, and granular event monitoring. Use when persisting arrays of items, building data controllers, or working with Boutique's Store type.