agentmods.dev

my-toybox: Command for Claude Code

.claude/commands/validate-screens.md

validate-screens is a command for Claude Code from Koshimizu-Takehito/my-toybox. It costs 0 tokens per session (1,155 once invoked), scanned A, original, MIT.

A validation command that checks whether an app's declared screen names, tags, and source files agree. It applies naming rules and verifies that each declared screen has an implementation.

In plain words
What is it for?
Use it to check the screen registry and its SwiftUI screen implementations before building or reviewing changes.
Why use it?
It catches mismatches such as a screen listed in the app but missing its Swift source file.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Koshimizu-Takehito/my-toybox's own configuration. It tells Claude Code how to work on my-toybox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my-toybox configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash Scripts/check_screen_sync.sh.

not rated 117repo 2mo ago A scan 0 tokens original MIT
View source ↗ Koshimizu-Takehito/my-toybox
Reuse

Borrowing it

Nothing to install: this file belongs to Koshimizu-Takehito/my-toybox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Koshimizu-Takehito/my-toybox/develop/.claude/commands/validate-screens.md
Clone the repo
git clone --depth 1 https://github.com/Koshimizu-Takehito/my-toybox

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 validate-screens

README.md
[![agentmods](https://agentmods.dev/badge/commands/koshimizu-takehito/my-toybox/validate-screens/github.svg)](https://agentmods.dev/commands/koshimizu-takehito/my-toybox/validate-screens)
Your own site
<a href="https://agentmods.dev/commands/koshimizu-takehito/my-toybox/validate-screens"><img src="https://agentmods.dev/badge/commands/koshimizu-takehito/my-toybox/validate-screens/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.

agentmods 80×15 button for validate-screens

Your own site · 80×15
<a href="https://agentmods.dev/commands/koshimizu-takehito/my-toybox/validate-screens"><img src="https://agentmods.dev/badge/commands/koshimizu-takehito/my-toybox/validate-screens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 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 $0.00000 $0.01155
Opus 5 $0.00000 $0.00577
Sonnet 5 $0.00000 $0.00231
Haiku 4.5 $0.00000 $0.00115

Measured 6d ago against content hash 2ce90ba781ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

validate-screens 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 6d 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/validate-screens.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screen Validator

Validate AppScreen.swift case names and synchronization with screen implementations.

Task

You are the screen-validator agent. Your mission is to ensure AppScreen.swift is valid, all screen case names are correctly formatted, and implementations exist for all declared screens.

Validation Steps

1. Screen Case Name Validation

  • Read Packages/Sources/AppScreens/AppScreen.swift
  • For each case in enum AppScreen:
    • Format Check: Case name must be a valid Swift identifier
      • Regex: ^[a-zA-Z_][a-zA-Z0-9_]*$
      • Must be lowerCamelCase
      • Should end with "Screen" suffix (convention)
    • Uniqueness Check: No duplicate case names

2. Tag Validation

  • Allowed tags (from Tag enum in MyToyboxCore): layout, animation, metal
  • Empty tags (tags: []) are allowed but non-empty tags are recommended
  • Warn if tags are empty, but do not treat as an error

3. Implementation Validation

For each case in AppScreen, verify the corresponding implementation exists:

Case to File Mapping:

  • Case: gameOfLifeScreen → File: Packages/Sources/Screens/GameOfLife/GameOfLifeScreen.swift
  • Convert lowerCamelCase case name to UpperCamelCase directory/file name
  • Remove "Screen" suffix for directory name
  • Add "Screen.swift" suffix for filename

Steps:

  1. Extract base name (e.g., gameOfLifeScreen → gameOfLife)
  2. Convert to UpperCamelCase (e.g., gameOfLife → GameOfLife)
  3. Check for directory: Packages/Sources/Screens/{BaseName}/
  4. Check for file: {BaseName}Screen.swift in that directory

4. Thumbnail Validation

For each screen, verify a +Thumbnail.swift file exists:

  • File: Packages/Sources/Screens/{BaseName}/{BaseName}Screen+Thumbnail.swift
  • Check that static func thumbnail(isScrolling:time:) is overridden (non-empty body)
  • The default implementation in ScreenMetadata returns an empty view — all screens should override it

5. Orphan Detection

Find screen implementations without AppScreen enum entries:

  • Scan Packages/Sources/Screens/ for all subdirectories
  • For each directory, check if a corresponding case exists in AppScreen.swift
  • Report any orphaned implementations

Read the full file on GitHub · 129 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. 6d ago First seen · 129 lines · 0 tokens per session scan A 2ce90ba781ff

Subscribe to this mod's changes

validate-screens is a command published in the GitHub repository Koshimizu-Takehito/my-toybox (117 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,155 tokens. 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 2026-09-04.

DebuggingMobile
Related

Other commands, from other repositories

flutter-build

Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.

affaan-m/ECC · 25 tokens

decompile

Decompile an Android APK/XAPK/JAR/AAR and analyze its structure.

CreditTone/android-reverse-engineering-skill · 15 tokens

safe-decompile

Safely fingerprint and decompile an Android artifact through the sandboxed MCP server.

salingnh/android-reverse-engineering-mcp · 16 tokens

proguard

Command "proguard" from getsentry/cli, covering examples, compute the uuid for a proguard/r8 mapping file, output as json (includes the file path) and important notes.

getsentry/cli · 0 tokens

debug

Debug Purchasely SDK issues — diagnose blank paywalls, frozen UI, purchase failures, and more.

Purchasely/Purchasely-AI-Plugin · 20 tokens

xcode-build-fix

Incrementally fix Xcode build and Swift compiler errors. Parse errors, explain issues, apply fixes, verify resolution.

OkminLee/everything-claude-code-ios · 23 tokens