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-ios-screenshotgit clone --depth 1 https://github.com/dmoskov/shadowskyWrote 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/commands/dmoskov/shadowsky/qa-ios-screenshot)<a href="https://agentmods.dev/commands/dmoskov/shadowsky/qa-ios-screenshot"><img src="https://agentmods.dev/badge/commands/dmoskov/shadowsky/qa-ios-screenshot.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00412 |
| Opus 5 | $0.00005 | $0.00206 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
qa-ios-screenshot 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 3d 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.
What it actually says
iOS Screenshot Analysis
Quick command to capture and analyze the current iOS simulator state.
Instructions
-
Take a screenshot:
xcrun simctl io booted screenshot /tmp/qa-ios-screenshot.png -
Read the screenshot image file to view it visually.
-
Analyze the screenshot for these visual issues:
Layout Issues
- Content clipped on left/right edges (text cut off, avatars partially hidden)
- Content overflowing beyond screen width
- Overlapping elements
- Incorrect z-ordering
Rendering Issues
- Gray placeholder circles where avatars should load
- Broken image embeds (gray rectangles with no content)
- Missing or malformed text (garbled characters, encoding issues)
- Incorrect colors or contrast
Spacing & Alignment
- Inconsistent padding between post cards
- Misaligned action bar icons (reply, repost, like, share)
- Tab bar icons not centered
- Text baseline misalignment between display name and timestamp
Interactive Elements
- Buttons that appear unresponsive (wrong styling)
- Missing tap targets
- Notification badges not rendering
Screen Identification
Identify which screen is currently showing:
- Home Feed: Shows post cards with avatars, text, embeds, action bar. Tab bar at bottom with Home highlighted.
- Search: Search bar at top, trending/suggested content
- Notifications: List of notification cells with icons (heart, repost, follow, mention)
- Profile: Banner image, avatar, display name, stats (posts/followers/following), tab bar (Posts/Replies/Media/Likes)
- Thread: Root post at top with nested reply cards below
- Login: Form with handle/email input, password input, sign in button
- Report findings with specific descriptions of what looks wrong and where on screen.
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.
- 3d ago First seen · 54 lines · 10 tokens per session scan A d0671e6253ae
qa-ios-screenshot is a command published in the GitHub repository dmoskov/shadowsky (17 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 412 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
test-simulator
Launch simulator testing agent for test scenarios and visual verification.
run-tests
Run XCUITests and parse results using the test-runner agent.
flutter-test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
ui-test
Run visual UI tests by comparing device screenshots against benchmark images. Supports ADB actions (tap, type, swipe, back, wait, launch) to navigate through app flows.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.