my-toybox: Command for Claude Code

.claude/commands/debug-build.md

debug-build is a command for Claude Code from Koshimizu-Takehito/my-toybox. It costs 0 tokens per session (1,930 once invoked), scanned A, original, MIT.

A troubleshooting guide for Swift and Metal builds in Xcode, Swift Package Manager plugins, and GitHub Actions. GitHub Actions is a service that runs automated build and test jobs.

In plain words
What is it for?
It helps diagnose xcodebuild errors, Metal compilation problems, code-generation plugin failures, test failures, and CI failures.
Why use it?
It gives a structured way to distinguish source-code, shader, plugin, test, and continuous-integration failures before applying a fix.

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/build_metallib.sh.

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/debug-build.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 debug-build

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/koshimizu-takehito/my-toybox/debug-build"><img src="https://agentmods.dev/badge/commands/koshimizu-takehito/my-toybox/debug-build.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 1,930 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 $0.01930
Opus 5 $0.00000 $0.00965
Sonnet 5 $0.00000 $0.00386
Haiku 4.5 $0.00000 $0.00193

Measured 5d ago against content hash d5fe6baa3627, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

debug-build 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 5d 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/debug-build.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Debugger

Diagnose and fix xcodebuild, SPM plugin, and CI build failures.

Task

You are the ci-debugger agent. Your mission is to diagnose build failures, test failures, and CI issues, then provide actionable fixes.

Build System Overview

MyToybox uses three build systems:

  1. xcodebuild: Main compilation via workspace (Swift, Metal, resources)
  2. SPM Plugins: Code generation (BuildMetalShaders)
  3. GitHub Actions CI: Automated validation

Diagnostic Steps

1. Identify Failure Type

Ask the user or determine from context:

  • Build failure: Won't compile
  • Test failure: Tests failing
  • Plugin failure: Code generation errors
  • CI failure: GitHub Actions failing

2. Build Failure Diagnosis

Run Full Build:

xcodebuild -workspace MyToybox.xcworkspace -scheme MyToybox \
  -destination 'platform=iOS Simulator,name=iPhone 17,OS=26.4' \
  CODE_SIGNING_ALLOWED=NO clean build

Common Build Errors:

Swift Compilation Errors
  • Symptom: "Type 'Foo' does not conform to protocol 'Bar'"
  • Diagnosis: Check protocol conformance, missing methods
  • Fix: Implement required protocol methods
Metal Compilation Errors
  • Symptom: "Compilation succeeded with warnings for file '...metal'"
  • Diagnosis: Check Metal shader syntax, function signatures
  • Fix: Review shader code, check [[stitchable]] attribute
  • Deep Dive: Look for .air file generation in build output
Missing Resources
  • Symptom: "Could not find resource '...'"
  • Diagnosis: Check Bundle.module access, resource bundle config
  • Fix: Verify file is in correct Resources/ directory
Macro Expansion Errors
  • Symptom: "Cannot find type 'XxxScreen' in scope" (from @Screens macro)
  • Diagnosis: The screen View type referenced by a Screen enum case does not exist
  • Fix: Create the missing View type in Packages/Sources/Screens/
Concurrency Errors (Swift 6)
  • Symptom: "Call to main actor-isolated ... from non-isolated context"
  • Diagnosis: Missing @MainActor annotation or improper async context
  • Fix: Add @MainActor or use await MainActor.run { ... }

Read the full file on GitHub · 242 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. 5d ago First seen · 242 lines · 0 tokens per session scan A d5fe6baa3627

Subscribe to this mod's changes

debug-build 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 1,930 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.