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 Dev869/swift-tothemax --skill app-review-maxgit clone --depth 1 https://github.com/Dev869/swift-tothemaxWrote 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/dev869/swift-tothemax/app-review-max)<a href="https://agentmods.dev/skills/dev869/swift-tothemax/app-review-max"><img src="https://agentmods.dev/badge/skills/dev869/swift-tothemax/app-review-max/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/dev869/swift-tothemax/app-review-max"><img src="https://agentmods.dev/badge/skills/dev869/swift-tothemax/app-review-max.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 | $0.00218 | $0.03026 |
| Opus 5 | $0.00109 | $0.01513 |
| Sonnet 5 | $0.00044 | $0.00605 |
| Haiku 4.5 | $0.00022 | $0.00303 |
Grade A, and why
app-review-max 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Review Max — Pass Review, Recover From Rejection
You own one outcome: the app gets approved. Audit like a reviewer, fix like a developer, and write reviewer-facing text like someone who wants a 24-hour turnaround.
Scope boundaries: privacy manifests, nutrition labels, GDPR/CCPA, and legal documents belong to apple-legal-max. Build numbers, phased release, and release automation belong to apple-release-ops. This skill covers everything App Review and QC: guideline compliance, pre-submission checks, rejection recovery, and reviewer communication.
How App Review Actually Works
Know the machine before you feed it:
- Upload-time automated checks. The moment a build hits App Store Connect, automated analysis scans for private API usage, missing usage-description strings, malformed Info.plist entries, missing privacy manifest declarations, and invalid entitlements. These produce ITMS errors/warnings by email — fix them before human review ever starts.
- Human review. A reviewer installs your build on a physical device (recent iOS, typically from a California/US network — plan geofencing and allowlists accordingly), reads your metadata, and exercises the app for minutes, not hours. They follow your App Review notes if you wrote any; they improvise if you didn't.
- Timeline. Apple states 90% of submissions are reviewed within 24 hours. Budget 24–48h per attempt, and assume at least one rejection cycle for first submissions — plan launch dates with a week of buffer.
- What reviewers see. Your binary, all metadata (name, subtitle, description, keywords, screenshots, previews), your privacy labels, the age-rating questionnaire, IAP products submitted with the build, and your App Review notes. They do NOT see your source code, your roadmap, or your intentions. If a feature is invisible or gated, it does not exist unless your notes make it exist.
- Rejection anatomy. Rejections arrive in App Store Connect (Resolution Center thread) citing specific guideline numbers, often with screenshots of the offending screen. Two flavors: binary rejected (fix requires a new build) and metadata rejected (fix the listing text/screenshots and resubmit the same build — much faster).
- Scale context. Apple reviews millions of submissions a year and rejects roughly a quarter of them. Rejection is routine process, not catastrophe. Treat the first rejection as a data point, not a verdict.
What ships with it
3 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.
- 9d ago First seen · 113 lines · 218 tokens per session scan A 3ced180717c6
app-review-max is a skill published in the GitHub repository Dev869/swift-tothemax (7 stars, last pushed 2mo ago), licensed MIT. It adds 218 tokens to every session and 3,026 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
app-store-review-guidelines
Route App Store submission-compliance tasks to the correct Knowledge Contracts — app completeness, demo accounts, screenshot/description accuracy, in-app purchase requirements, external payment link restrictions, restore purchases, minimum functionality, spam/duplicate-app avoidance, permission usage strings, privacy…
privacy
Route Privacy Manifest (PrivacyInfo.xcprivacy) implementation tasks to the correct Knowledge Contracts -- file structure/bundling, required-reason API declarations, collected data type declarations, and tracking domains/third-party SDK signatures. Use when writing or editing PrivacyInfo.xcprivacy…
ipaship-audit
Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.
backgroundtasks
Route BackgroundTasks implementation tasks to the correct Knowledge Contracts -- background task registration and scheduling, task execution and expiration handling, processing task constraints and conditions, and background refresh and widget timeline hookup. Use when registering a task identifier with…
core-data
Route Core Data implementation tasks to the correct Knowledge Contracts -- subclassing NSManagedObject and choosing an .xcdatamodeld Codegen mode (Class Definition/Manual-None/Category+Extension) with @NSManaged properties, standing up NSPersistentContainer via loadPersistentStores(completionHandler:) and viewContext…
core-location
Route Core Location implementation tasks to the correct Knowledge Contracts -- authorization and usage strings, location updates and delivery, accuracy and precise location, and background monitoring with location-triggered launches. Use when reading CLAuthorizationStatus or authorizationStatus, calling…