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 app-rejection-recoverygit 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/app-rejection-recovery)<a href="https://agentmods.dev/skills/markdavidgan/apple-dev-skills/app-rejection-recovery"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/app-rejection-recovery/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/app-rejection-recovery"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/app-rejection-recovery.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 | $0.00132 | $0.03782 |
| Opus 5 | $0.00066 | $0.01891 |
| Sonnet 5 | $0.00026 | $0.00756 |
| Haiku 4.5 | $0.00013 | $0.00378 |
Grade A, and why
app-rejection-recovery 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 12d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Rejection Recovery
Diagnose Apple App Review rejections fast, write a response that gets re-reviewed within 24 hours, and ship the fix before your launch window closes.
Step 1 — Triage before you type a single word
Do not draft anything until you have answers to all of the following:
- Paste the full rejection verbatim — every sentence, including the guideline number(s). Paraphrasing loses signal.
- First submission or update? First submissions face higher scrutiny; updates that regress on a previously approved flow are a separate failure mode.
- What changed in this version? A clean diff of what's new (features, SDKs, entitlements, Info.plist keys) narrows root cause immediately.
- Is this time-sensitive? Marketing tied to a date, a live event, or a partner launch — that changes the escalation path.
- App category and monetization model — required to assess 3.x IAP and 5.x privacy exposure.
Use asc_get_review_detail (App Store Connect MCP) to pull the current review state and any inline reviewer notes if the user hasn't already copied them.
Apple Rejection Taxonomy
| Guideline | Bucket | Typical Fix |
|---|---|---|
| 2.1 | Performance / completeness | Reproduce crash on reviewer's device + iOS; ship fixed binary with demo account |
| 2.1(b) | IAP won't purchase | Check Paid Apps Agreement is Active in ASC Business, not Pending User Info; confirm no environment-gated fallback masks a real StoreKit error |
| 2.2 | Beta-testing features shipped in production | Remove any UI/copy/control that only exists to support testers — see the environment-vs-identity gating pitfall below |
| 2.3.x | Accurate metadata | Screenshots must match live binary; no unsupported device mentions |
| 2.5.x | Software requirements | Remove private API use; correct HealthKit / CallKit / SiriKit misuse |
| 3.1.1 | IAP — digital goods | All digital content sold through StoreKit; no external payment links |
| 3.1.2 | IAP — subscriptions | Auto-renewal disclosure on screen; restore purchases button; terms link |
| 3.2.2 | Unacceptable business model | MLM, lottery without license, or misleading monetization |
| 4.0 | Design | Broken layout, non-functional UI, copycat shell |
| 4.2 | Minimum functionality | Web wrapper, thin brochureware, or single-static-page app |
| 4.3 | Spam / duplicate | Substantive differentiation from your own or competitor portfolio required |
| 4.5.x | Apple sites and services | Correct Apple logo usage; no push-notification abuse |
| 5.1.1 | Privacy — data collection | Privacy policy URL live; App Privacy labels accurate; ATT copy specific |
| 5.1.2 | Data use and sharing | Privacy nutrition labels must reflect every SDK's collection, not just first-party |
| 5.1.5 | Location services | "Always" permission must be demonstrably necessary; "When In Use" for most apps |
| 5.1.7 | Health and medical | Disclaimers required; no diagnostic claims without regulatory clearance |
| 5.2.x | Intellectual property | Trademark or copyright holder permission in writing |
| 5.3.x | Gaming and gambling | Valid regional license required for real-money wagering |
| 5.6.1 | Developer code of conduct | Fake reviews, review manipulation, spam across apps |
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.
- 12d ago First seen · 278 lines · 132 tokens per session scan A 54ac0fbf35cc
app-rejection-recovery is a skill published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 13d ago), licensed MIT. It adds 132 tokens to every session and 3,782 once invoked, about $0.0007 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
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-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-metadata-sync
Sync, validate, and apply App Store metadata with the current asc canonical metadata workflow. Use when updating metadata, localizations, keywords, or migrating legacy fastlane metadata.
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…
asc-submission-health
Diagnose App Store submission blockers and operate review health with asc, including readiness validation, repair routing, status monitoring, cancellation, and retry decisions. Use when validation fails, a version is not in a valid state, review status is unclear or stuck, or a failed submission must be repaired and…