qa-ios-screenshot

qa-ios-screenshot is a command for Claude Code from dmoskov/shadowsky. It costs 10 tokens per session (412 once invoked), scanned A, original, MIT.

A command that captures the current iOS Simulator screen and checks the image for visual problems.

In plain words
What is it for?
Use it to review iOS screens for clipped content, overlapping elements, broken images, incorrect colors, misplaced icons, missing buttons, and other visible defects.
Why use it?
It helps find layout, rendering, spacing, alignment, and touch-target issues without inspecting the app only through code.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dmoskov/shadowsky/qa-ios-screenshot
Clone the repo
git clone --depth 1 https://github.com/dmoskov/shadowsky

Made for: Claude Code.

Wrote 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.

agentmods badge for qa-ios-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/commands/dmoskov/shadowsky/qa-ios-screenshot.svg)](https://agentmods.dev/commands/dmoskov/shadowsky/qa-ios-screenshot)
Your own site
<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>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash d0671e6253ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/qa-ios-screenshot.md · 54 lines

What it actually says

iOS Screenshot Analysis

Quick command to capture and analyze the current iOS simulator state.

Instructions

  1. Take a screenshot:

    xcrun simctl io booted screenshot /tmp/qa-ios-screenshot.png
    
  2. Read the screenshot image file to view it visually.

  3. 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
  1. Report findings with specific descriptions of what looks wrong and where on screen.
Changes

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.

  1. 3d ago First seen · 54 lines · 10 tokens per session scan A d0671e6253ae

Subscribe to this mod's changes

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.