agentmods.dev

shadowsky: Command for Claude Code

.claude/commands/qa-ios-build.md

qa-ios-build is a command for Claude Code from dmoskov/shadowsky. It costs 13 tokens per session (403 once invoked), scanned A, original, MIT.

A command that builds an iOS app and reports whether compilation succeeded, including errors, warnings, file locations, and suggested fixes when available.

In plain words
What is it for?
Use it to verify an Expo iOS app, investigate compiler errors, group related failures, and check warnings.
Why use it?
It provides a repeatable check for build failures instead of relying on a developer to inspect long build output manually.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

This is dmoskov/shadowsky's own configuration. It tells Claude Code how to work on shadowsky 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 shadowsky configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/moskov/Code/BSKY/mobile.

not rated 17repo 1mo ago A scan 13 tokens original MIT
View source ↗ dmoskov/shadowsky shadowsky.io
Reuse

Borrowing it

Nothing to install: this file belongs to dmoskov/shadowsky. 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/dmoskov/shadowsky/main/.claude/commands/qa-ios-build.md
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-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/dmoskov/shadowsky/qa-ios-build/github.svg)](https://agentmods.dev/commands/dmoskov/shadowsky/qa-ios-build)
Your own site
<a href="https://agentmods.dev/commands/dmoskov/shadowsky/qa-ios-build"><img src="https://agentmods.dev/badge/commands/dmoskov/shadowsky/qa-ios-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 qa-ios-build

Your own site · 80×15
<a href="https://agentmods.dev/commands/dmoskov/shadowsky/qa-ios-build"><img src="https://agentmods.dev/badge/commands/dmoskov/shadowsky/qa-ios-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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 $0.00013 $0.00403
Opus 5.5 $0.00005 $0.00161
Sonnet 5.5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00040

Measured 1mo ago against content hash 6eb445d6bed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa-ios-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 1mo 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-build.md · 47 lines

What it actually says

iOS Build Verification

Build the iOS app and report success or failure.

Instructions

  1. Run the iOS build from the mobile directory:

    cd /Users/moskov/Code/BSKY/mobile && npx expo run:ios --no-install

    Use a 5-minute timeout since builds can be slow.

  2. Parse the build output:

    • Look for Build Succeeded or Build Failed
    • Count errors and warnings
    • For errors, report the file path, line number, and error message
    • For warnings, note them but focus on errors first

  3. If the build fails:

    • Read the failing file(s) to understand the error context
    • Suggest a fix for each error
    • Group related errors (e.g., multiple errors from a single bad import)

  4. Report results:

    Build: PASS/FAIL
Errors: N
Warnings: N

[If failed, list each error with file:line and suggested fix]

Common Build Errors

Error Cause Fix
cannot find type 'X' in scope Missing import or access control Add import or mark type as public
'X' is only available in iOS N.0 or newer API too new for deployment target (15.1) Use older API or add availability check
use of unresolved identifier Typo or missing import Check spelling, add import
expression type 'X' is ambiguous SwiftUI view builder inference failure Add explicit type annotations
missing argument for parameter Struct initializer changed Update call sites to match new signature
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. 1mo ago First seen · 47 lines · 13 tokens per session scan A 6eb445d6bed2

Subscribe to this mod's changes

qa-ios-build is a command published in the GitHub repository dmoskov/shadowsky (17 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 403 once invoked, about $0.0001 per session on Opus 5.5. 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.

MobileTesting
Related

Other commands, from other repositories

xcode-test

Build and test iOS apps on simulator using XcodeBuildMCP.

davekilleen/Dex · 18 tokens

axiom-ui

Drive simulator UI with Axiom xcui or compatible AXe input verbs.

CharlesWiltgen/Axiom · 18 tokens

generate-widget

Génération Widget Flutter avec Tests.

TheBeardedBearSAS/claude-craft · 7 tokens

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.

Lykhoyda/rn-dev-agent · 30 tokens

dev-flutter

Create Flutter widgets, screens and features with Clean Architecture.

christopherlouet/claude-base · 0 tokens

flutter-test

Run Flutter tests with coverage reporting (unit, widget, integration).

smicolon/ai-kit · 16 tokens