swift-diagnose

swift-diagnose is a skill for Claude Code from charlesjones-dev/claude-code-plugins-dev. It costs 83 tokens per session (2,230 once invoked), scanned A, original, MIT.

A Swift and Apple-platform failure diagnostician. It reads a pasted Xcode Cloud build log, TestFlight or App Store rejection, keychain error, or error code and explains the likely cause and fix.

In plain words
What is it for?
Use it to investigate failed Xcode Cloud builds, App Store Connect rejections, TestFlight uploads, signing problems, and runtime keychain errors.
Why use it?
It turns hard-to-interpret signing, entitlement, upload, and build failures into a specific diagnosis instead of requiring manual searching through logs and Apple error codes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ai-swift plugin — 5 skills, 1 agent shipped together

Good fit Use it to investigate failed Xcode Cloud builds, App Store Connect rejections, TestFlight uploads, signing problems, and runtime keychain errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/charlesjones-dev/claude-code-plugins-dev/swift-diagnose
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.

Any agent
npx skills add charlesjones-dev/claude-code-plugins-dev --skill swift-diagnose
Clone the repo
git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code.

Or install ai-swift, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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 swift-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-diagnose.svg)](https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/swift-diagnose)
Your own site
<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/swift-diagnose"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,230 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 41
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 53
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 19
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 36
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 37
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 49
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00083 $0.02230
Opus 5 $0.00042 $0.01115
Sonnet 5 $0.00017 $0.00446
Haiku 4.5 $0.00008 $0.00223

Measured yesterday against content hash 9bd9710f4f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swift-diagnose 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 yesterday.

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.

plugins/ai-swift/skills/swift-diagnose/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift Failure Diagnostician

You are a triage engineer for Apple-platform build and release failures. The user gives you a symptom: a red Xcode Cloud build log, an ITMS rejection email from App Store Connect, a runtime keychain error, or just an error code. You identify the root cause from the catalog below and prescribe the precise fix, including the "why" so the user recognizes it next time.

This is the reactive counterpart to /swift-preflight (which is proactive). Use it when something already went red.

Input

$ARGUMENTS may contain the pasted text directly, or a path to a log file, or just a code like ITMS-90296 or -25293. If it is a path, read the file. If it is empty, ask the user to paste the failing log / email / code.

When a repo is available in the working directory, also inspect it to ground the fix: read project.yml, the entitlements file, ci_scripts/, Info.plist, and the relevant test/source files so your remedy cites real file:line locations rather than generic advice.

Method

  1. Classify the symptom. Match against the catalog. Symptoms often arrive in clusters (an upload can trigger ITMS-90242 + ITMS-90296 in the same email); enumerate all of them.
  2. Locate the cause in the repo (if present). Confirm the diagnosis against the actual files.
  3. Prescribe the fix with concrete edits and the one-line why. Note whether the fix is repo-side (you can do it / hand to a writer skill) or App Store Connect UI-side (you can only describe the clicks).
  4. Prevent recurrence. Point at the /swift-preflight check number that would have caught it before upload.

Catalog

App Store processing rejections (ITMS-*, arrive by email after upload)

These are not build failures. The archive succeeded, the upload succeeded, and the rejection arrives during processing. That is why they surprise people.

  • ITMS-90242 — missing LSApplicationCategoryType. Info.plist has no app category, or it is not a valid category UTI. Fix: add LSApplicationCategoryType with a valid UTI (e.g. public.app-category.news, public.app-category.productivity). On XcodeGen, add it under the target's info.properties in project.yml (which merges into Info.plist on generate), not directly in the plist. Match the primary category set in App Store Connect. Prevent: /swift-preflight Check 4.

Read the full file on GitHub · 104 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. yesterday First seen · 104 lines · 83 tokens per session scan A 9bd9710f4f33

Subscribe to this mod's changes

swift-diagnose is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,230 once invoked, about $0.0004 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 2026-09-06.

Related

Other skills, from other repositories

axiom-background-processing

Use when implementing BGTaskScheduler, debugging background tasks that never run, understanding why tasks terminate early, or testing background execution - systematic task lifecycle management with proper registration, expiration handling, and Swift 6 cancellation patterns.

ComeOnOliver/skillshub · 47 tokens

axiom-networking-diag

Use when debugging connection timeouts, TLS handshake failures, data not arriving, connection drops, performance issues, or proxy/VPN interference - systematic Network.framework diagnostics with production crisis defense.

ComeOnOliver/skillshub · 42 tokens

axiom-now-playing

Use when Now Playing metadata doesn't appear on Lock Screen/Control Center, remote commands (play/pause/skip) don't respond, artwork is missing/wrong/flickering, or playback state is out of sync - provides systematic diagnosis, correct patterns, and professional push-back for audio/video apps on iOS 18+.

ComeOnOliver/skillshub · 69 tokens

axiom-combine-patterns

Use when working with Combine publishers, AnyCancellable lifecycle, @Published properties, or bridging Combine with async/await. Covers reactive patterns, operator selection, memory management, and migration strategy.

ComeOnOliver/skillshub · 45 tokens

axiom-energy-ref

Complete energy optimization API reference - Power Profiler workflows, timer/network/location/background APIs, iOS 26 BGContinuedProcessingTask, MetricKit monitoring, with all WWDC code examples.

ComeOnOliver/skillshub · 42 tokens

axiom-energy

Use when app drains battery, device gets hot, users report energy issues, or auditing power consumption - systematic Power Profiler diagnosis, subsystem identification (CPU/GPU/Network/Location/Display), anti-pattern fixes for iOS/iPadOS.

ComeOnOliver/skillshub · 52 tokens