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 MartinPuli/createAnApp --skill app-review-recoverygit clone --depth 1 https://github.com/MartinPuli/createAnAppWrote 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/martinpuli/createanapp/app-review-recovery)<a href="https://agentmods.dev/skills/martinpuli/createanapp/app-review-recovery"><img src="https://agentmods.dev/badge/skills/martinpuli/createanapp/app-review-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/martinpuli/createanapp/app-review-recovery"><img src="https://agentmods.dev/badge/skills/martinpuli/createanapp/app-review-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 | $0.00069 | $0.00767 |
| Opus 5 | $0.00034 | $0.00383 |
| Sonnet 5 | $0.00014 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
app-review-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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Review Recovery
Treat the reviewer message, attachments, tested devices, version/build, and submission item set as authoritative incident evidence. Do not resubmit after changing text alone unless the root cause is proven to be metadata-only.
Read references/rejection-catalog.md to classify common signals and references/rejection-patterns.md for operational controls, but let the exact current reviewer evidence override both.
Preserve the incident
Record submission ID, review date, exact app version/build, review devices/OS, guideline, full message, screenshots/attachments, affected items/statuses, prior responses, and current storefront/build state. Redact reviewer contact and account data from public repositories.
Classify root cause
Map each issue to one or more layers:
- code/functionality;
- supported-device design/accessibility;
- commerce/StoreKit;
- metadata/screenshot/URL;
- privacy/security/legal/content rights;
- account/agreement/configuration;
- review access/instructions/environment;
- submission dependency/state.
Read the current cited guideline and linked Apple help. Look for additional contradictions; do not assume the first visible issue is the only one.
Reproduce the reviewer path
Use the exact build and closest available review device/OS. Start from a clean install and follow the supplied screenshots/message. Inspect adaptive widths, localization, permissions, offline/network conditions, logged-out/gated states, StoreKit availability, and review credentials.
If exact reproduction is impossible, state the gap and test conservative variants.
Implement the systemic fix
Fix every instance, not only the screenshot location. Update source, tests, design system, supported-device declaration, metadata, policies, and review notes as affected. Use a new build for binary changes.
Common controls:
- Subscription EULA: functional Terms link in description when using the standard Apple EULA, or configured custom EULA; verify paywall/legal links too.
- Crowded UI: redesign compact widths; do not simply shrink fonts. Audit every supported family/orientation/Dynamic Type size.
- New subscription group: submit group plus at least one product and required new app version in the same submission.
- Returned commerce items: repair and re-add the complete app/group/product dependency set.
- Stuck screenshots: delete, valid RGB re-export, small-batch upload, save, and inspect every Media Manager well.
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.
- 11d ago First seen · 73 lines · 69 tokens per session scan A 3ce95625f69d
app-review-recovery is a skill published in the GitHub repository MartinPuli/createAnApp (14 stars, last pushed 21d ago), licensed MIT. It adds 69 tokens to every session and 767 once invoked, about $0.0003 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
workflow-audit
Systematic UI workflow auditing for SwiftUI applications. Discovers entry points, traces user flows, detects dead ends and broken promises, audits data wiring, evaluates from user perspective. Triggers: "workflow audit", "audit flows", "find dead ends", "check navigation".
ttb-skill-bugfix
Systematic bug fixing workflow for TTBaseUIKit apps: root cause analysis, fix strategy, xcodebuild verify, zero regression.
ax-performance
Use when app feels slow, memory grows, hangs occur, frame rate issues, or profiling needed - covers Instruments workflows, memory debugging, hang diagnostics, display performance, MetricKit, xctrace CLI, and ObjC block retain cycles.
swiftui-performance
Profiles and fixes SwiftUI runtime performance with code review, Instruments, and repeatable measurement. Use for slow rendering, scrolling or animation hitches, excessive body updates, identity churn, layout spikes, broad Observation invalidation, CPU cost, or before/after verification.
ios-ettrace-performance
Use when capturing or analyzing ETTrace profiles for a focused iOS launch or runtime flow, including exact-build dSYM UUID matching, Simulator or device capture, processed per-thread flamegraph JSON, sampled inclusive/exclusive time, unresolved symbols, and comparable verification. Use debugging-instruments or…
ios-memgraph-analysis
Captures or analyzes iOS memgraph files and persistent heap growth with Apple CLI evidence, ownership paths, raw artifacts, and matched-flow verification. Use for leaks or memory-growth investigations; route interactive Xcode Memory Graph, Instruments, or LLDB work to debugging-instruments.