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 ratings-mechanicsgit 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/ratings-mechanics)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/ratings-mechanics"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/ratings-mechanics/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/ratings-mechanics"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/ratings-mechanics.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 | $0.00075 | $0.01283 |
| Opus 5 | $0.00037 | $0.00642 |
| Sonnet 5 | $0.00015 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
ratings-mechanics 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ratings Mechanics
The rating is an asset with mechanics most developers learn the hard way. This skill covers the
four rules that aren't obvious from the ASC UI. Prompting code lives in
generators/review-prompt; reply writing lives in app-store/review-response-writer — this
skill is the strategy layer that tells you when each matters.
When This Skill Activates
- Localizing or expanding into new storefronts ("why does my app show no rating in Japan?")
- Considering the "reset ratings summary" option on a version release
- Choosing release options before submitting (phased vs immediate, auto vs manual)
- Planning a per-market ratings strategy alongside
product/localization-strategy - A bad build or review-bomb is threatening the rating
Rule 1: Ratings are per-storefront — they do not travel
Your 4.8★ from 2,000 US ratings renders as no rating at all on the Japanese storefront until Japanese users rate the app there. Every storefront starts from zero.
Consequences:
- ✅ Entering a new market = re-running the early-days ratings playbook in that market: prompt eagerly (within guidelines), localize the prompt moment, reply to every early review.
- ✅ Weight
requestReviewtriggers by storefront maturity — a market with 12 ratings needs the prompt more than the home market with 5,000. - ❌ Assuming social proof transfers with the binary. A localized listing with zero local ratings converts like an unknown app, because there it is one.
- The written-review pool is also per-storefront: expect empty review sections in fresh markets and seed them via TestFlight communities or launch outreach in that region.
Rule 2: Never reset the ratings summary
ASC offers a reset when you release a new version. It is almost always a mistake:
- Reset discards the count as well as the average — 4.2★ from 3,000 ratings converts better than a naked 5.0★ from 6, and the count never comes back except one rating at a time.
- The instinct to reset ("v2 is a big rewrite, old reviews don't apply") is better served by
replying to outdated negative reviews (updated ratings replace the old score — see
review-response-writer) and by the What's New copy. - ✅ Legitimate near-exception: a catastrophic launch (sub-3★, low count, fixed root cause) on an app with almost no ratings mass. Even then, run the math on count loss first.
- ❌ Resetting an established app to chase a higher average. You'll rank and convert worse for months.
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.
- 11d ago First seen · 97 lines · 75 tokens per session scan A 0f12950688f4
ratings-mechanics is a skill published in the GitHub repository rshankras/claude-code-apple-skills (719 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,283 once invoked, about $0.0004 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-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.