screenshot-validator

screenshot-validator is an agent for Claude Code from CharlesWiltgen/Axiom. It costs 205 tokens per session (2,452 once invoked), scanned A, original, MIT.

A visual checker for App Store screenshots, the images submitted with an iPhone or iPad app listing. It reviews images for dimensions, broken interface elements, placeholders, debug traces, and competitor references.

In plain words
What is it for?
It helps inspect a folder of screenshots and report incorrect sizes, placeholder text, debug indicators, broken UI, and mentions of competitors.
Why use it?
It helps catch screenshot problems before App Store submission, including issues that may lead to rejection or make the app look unfinished.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter; positional $N argument; mentions Claude Code.

Part of the axiom plugin — 27 skills, 17 commands, 42 agents, 5 hooks shipped together

Good fit It helps inspect a folder of screenshots and report incorrect sizes, placeholder text, debug indicators, broken UI, and mentions of competitors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charleswiltgen/axiom/screenshot-validator
About the project

Axiom is a toolkit of instructions, agents, commands, and development tools that give coding assistants specialized guidance for Apple operating-system development. It covers Swift, SwiftUI, interface design, data, concurrency, performance, networking, accessibility, logging, crash analysis, simulator testing, and profiling for iOS, iPadOS, watchOS, and tvOS. The catalogue contains 42 agents, 16 commands, and one plugin from this toolkit.

CharlesWiltgen/Axiom · 1,148 stars · on GitHub · charleswiltgen.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/CharlesWiltgen/Axiom

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 27 skills, 17 commands, 42 agents, 5 hooks.

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 screenshot-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/charleswiltgen/axiom/screenshot-validator.svg)](https://agentmods.dev/agents/charleswiltgen/axiom/screenshot-validator)
Your own site
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/screenshot-validator"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/screenshot-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 205 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00205 $0.02452
Opus 5 $0.00102 $0.01226
Sonnet 5 $0.00041 $0.00490
Haiku 4.5 $0.00020 $0.00245

Measured 7d ago against content hash 936ee0a11ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

screenshot-validator 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 7d 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-plugin/plugins/axiom/agents/screenshot-validator.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Store Screenshot Validator Agent

You are an expert at reviewing App Store screenshots for compliance, quality, and content issues before submission. You use Claude's multimodal vision to visually inspect each screenshot.

Your Mission

Validate App Store screenshots against Apple's submission requirements and catch issues that would cause rejection or hurt conversion — placeholder text, wrong dimensions, debug artifacts, broken UI, and competitor references.

Step 1: Get Screenshot Folder

If no folder path was provided in the prompt, ask the user:

"Where are your App Store screenshots? Please provide the folder path (e.g., ~/Desktop/Screenshots or ./marketing/screenshots)."

Do not proceed without a folder path.

Step 2: Discover Screenshots

Use the Glob tool to find all image files:

Glob: <folder_path>/**/*.png
Glob: <folder_path>/**/*.jpg
Glob: <folder_path>/**/*.jpeg

Count the results. If 0 images found, report and stop.

If more than 20 images found, tell the user:

"Found [N] screenshots. To keep analysis thorough, I'll check the first 20. If you'd like me to focus on a specific subset (e.g., one device size or one locale), let me know."

Then proceed with the first 20.

Step 3: Dimension Check

Run batch dimension checking on the files discovered in Step 2:

# Check dimensions for all screenshots from Step 2 Glob results
for f in "<file1>" "<file2>" "<file3>"; do
  sips -g pixelWidth -g pixelHeight "$f" 2>/dev/null
done

Match each screenshot against required App Store sizes:

Required Device Screenshots

Device Portrait Landscape
iPhone 6.9" (16 Pro Max) 1320 × 2868 2868 × 1320
iPhone 6.7" (15 Plus/Pro Max) 1290 × 2796 2796 × 1290
iPhone 6.5" (11 Pro Max/Xs Max) 1242 × 2688 2688 × 1242
iPhone 5.5" (8 Plus) 1242 × 2208 2208 × 1242
iPad 13" (Pro M4) 2064 × 2752 2752 × 2064
iPad 12.9" (Pro 6th gen) 2048 × 2732 2732 × 2048

Read the full file on GitHub · 261 lines

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. 7d ago First seen · 261 lines · 205 tokens per session scan A 936ee0a11ff9

Subscribe to this mod's changes

screenshot-validator is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,148 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 2,452 once invoked, about $0.0010 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.

Related

Other agents, from other repositories

verifier

Read-only iOS build/test/log checker for the QRSPI Implement-phase loop. Backend-agnostic: prefers the Xcode 27 native xcode-tools MCP server when running inside Xcode (BuildProject, RunProject, Issue Navigator diagnostics), falls back to XcodeBuildMCP when running externally (Claude Code CLI), and to raw xcodebuild…

Vvlladd/qrspi-orchestrator · 117 tokens

android-emulator-tester

Automated Android UI/integration testing specialist; the agent that drives a real Android app on a headless emulator under WSL/Linux and gates on what it observes. Use when the task is "run the app on an emulator", "smoke-test a screen", "drive the Android UI", "reproduce a tap-and-crash / ANR", "automate an Android…

simiancraft/simiancraft-skills · 247 tokens

mobile-mobile-qa

Mobile QA engineer that tests mobile applications, performs device testing, and ensures quality.

MonumentalSystems/Atlas-Agent-Teams · 20 tokens

mobile-tester

Tests a Flutter or mobile app like a real user on an Android AVD or iOS simulator, verifying with parsed screenshots and integration tests. - Use when an app build needs a real run on an emulator or simulator, with screenshots as evidence. Read-only on source; reports pass/fail with evidence paths. Spawn one per app…

uwuclxdy/agenticat · 73 tokens

testing-specialist

XCTest, Swift Testing, TDD, and quality assurance.

CarolaneLFBV/ios-development-agents · 27 tokens

xcuitest-runner

XCUITest E2E testing specialist for iOS. Use PROACTIVELY for generating, maintaining, and running UI tests. Manages test journeys, quarantines flaky tests, captures screenshots/videos, and ensures critical user flows work.

OkminLee/everything-claude-code-ios · 54 tokens