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 agentmods add commands/dmoskov/shadowsky/qa-iosgit clone --depth 1 https://github.com/dmoskov/shadowskyWhat 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 | $0.00018 | $0.00950 |
| Opus 5 | $0.00009 | $0.00475 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
qa-ios 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS QA Pass
Run a comprehensive QA pass on the iOS app. This includes visual screenshot analysis, code-level review of all native SwiftUI modules, and a layout pattern audit.
Prerequisites
- iOS Simulator must be booted with the app running
- Booted device: !
xcrun simctl list devices booted 2>/dev/null | head -3
Step 1: Visual Screenshot Analysis
- Take a screenshot of the current simulator state:
xcrun simctl io booted screenshot /tmp/qa-ios-current.png - Read the screenshot image and analyze for visual issues:
- Content clipping (text cut off, avatars invisible)
- Layout overflow (content extending beyond screen bounds)
- Missing images or broken placeholders
- Incorrect spacing or alignment
- Tab bar rendering issues
- Status bar overlap with content
Step 2: Native SwiftUI Module Review
Review each native iOS module for issues. Read the key files and check for problems.
Module Paths
| Module | Key Files |
|---|---|
| Feed List | mobile/modules/native-feed-list/ios/FeedListView.swift, PostCardView.swift, FeedListModule.swift |
| Profile | mobile/modules/native-profile-view/ios/ProfileView.swift, ProfileHeaderView.swift |
| Embeds | mobile/modules/expo-swiftui-feed/ios/Sources/ExpoSwiftUIFeed/PostEmbed.swift, ImageEmbed.swift, VideoEmbed.swift, ExternalLinkEmbed.swift, QuoteEmbed.swift |
| Rich Text | mobile/modules/rich-text-view/ios/RichTextView.swift |
Code Review Checklist
For each module, check:
- No
.fixedSize(horizontal: false, vertical: true)inside ScrollView/LazyVStack (causes width overflow) - No
UIScreen.main.boundsfor layout calculations (use GeometryReader instead) - UIViewRepresentable views have
setContentCompressionResistancePriority(.defaultLow, for: .horizontal) - Text views in scrollable containers use
.frame(maxWidth: .infinity, alignment: .leading)not.fixedSize - AsyncImage has proper placeholder and failure states
- Event handlers are properly wired (onPress, onLike, onRepost, etc.)
- NotificationCenter observers are properly cleaned up in
stopObserving()/deinit - No retain cycles in closures (use
[weak self])
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.
- yesterday First seen · 87 lines · 18 tokens per session scan A f2e4693f94f3
qa-ios is a command published in the GitHub repository dmoskov/shadowsky (17 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 950 once invoked, about $0.0001 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 2026-09-01.
Other commands, from other repositories
implement
yes, thank you! please proceed with implementation.
suggest-solution
if there is better solution, please suggest it.
android
Command "android" from zhagqn/agentwork, covering /android [subcommand] [args] and 执行前必读.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
mobile-performance-check
Analyze mobile app for performance issues using the mobile-best-practices database.