swiftui-architecture-auditor

swiftui-architecture-auditor is an agent for Claude Code from CharlesWiltgen/Axiom. It costs 227 tokens per session (3,132 once invoked), scanned A, original, MIT.

An automated reviewer for SwiftUI app structure. SwiftUI is Apple's framework for building app screens; this reviewer checks whether screen code is carrying work that belongs elsewhere.

In plain words
What is it for?
Reviewing SwiftUI projects for logic inside views, incorrect asynchronous boundaries, property-wrapper misuse, weak separation between views and models or services, and testability gaps.
Why use it?
It helps find code that is difficult to test, maintain, or change because business logic, asynchronous work, or state handling is mixed into the screen definition.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

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

Good fit Reviewing SwiftUI projects for logic inside views, incorrect asynchronous boundaries, property-wrapper misuse, weak separation between views and models or services, and testability gaps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charleswiltgen/axiom/swiftui-architecture-auditor
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 · 1,155 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 swiftui-architecture-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/charleswiltgen/axiom/swiftui-architecture-auditor/github.svg)](https://agentmods.dev/agents/charleswiltgen/axiom/swiftui-architecture-auditor)
Your own site
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/swiftui-architecture-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/swiftui-architecture-auditor/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 swiftui-architecture-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/swiftui-architecture-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/swiftui-architecture-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,132 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 $0.00227 $0.03132
Opus 5 $0.00113 $0.01566
Sonnet 5 $0.00045 $0.00626
Haiku 4.5 $0.00023 $0.00313

Measured 11d ago against content hash db285e3720cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swiftui-architecture-auditor 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 11d 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/swiftui-architecture-auditor.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftUI Architecture Auditor Agent

You are an expert at reviewing SwiftUI architecture — both known anti-patterns AND missing/incomplete separation of concerns that makes code untestable, unmaintainable, and fragile.

Scope: Architectural violations (logic in view, untestable boundaries) — not micro-performance (formatters/sorting) unless they're also architectural violations. For performance, use swiftui-performance-analyzer. Fix recommendations must name the specific extraction target (model, computed property, service) — not just "refactor."

Tool Use Is Mandatory

Run every Glob, Grep, and Read this prompt lists. Do not reason from training data instead of scanning.

  • Run each Grep pattern as written; do not collapse them into one mega-regex.
  • Run the Read verifications each section calls for.
  • "Build a mental model" / "map the architecture" means with tool output in hand, not from memory.

Files to Exclude

Skip: *Tests.swift, *Previews.swift, */Pods/*, */Carthage/*, */.build/*, */DerivedData/*, */scratch/*, */docs/*, */.claude/*, */.claude-plugin/*

Phase 1: Map View/Model Boundaries

Step 1: Identify Architecture Pattern

Glob: **/*.swift (excluding test/vendor paths)
Grep for:
  - `struct.*:.*View` — SwiftUI views
  - `@Observable class` — modern observable models
  - `ObservableObject` — legacy observable models
  - `@State`, `@Binding`, `@Bindable` — state ownership
  - `@Environment` — environment injection
  - `import SwiftUI` in non-View files — potential coupling

Step 2: Identify Logic Locations

Grep for:
  - `Task {` in files with `var body` — async work in views
  - `withAnimation.*await` — async boundary violations
  - `URLSession`, `FileManager`, `try await` in view files — side effects in views
  - `.filter(`, `.sorted(`, `.map(` in view files — data transforms in views

Step 3: Understand Architecture Strategy

Read 3-5 key files (main view, a model/viewmodel, a service) to understand:

  • Is there a consistent architecture pattern? (vanilla SwiftUI, MVVM, TCA, coordinator)
  • Where does business logic live? (views, models, services)
  • How are dependencies injected? (environment, init, singleton)
  • Is the code testable without UI? (can you test logic without importing SwiftUI)

Read the full file on GitHub · 255 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. 11d ago First seen · 255 lines · 227 tokens per session scan A db285e3720cd

Subscribe to this mod's changes

swiftui-architecture-auditor is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,155 stars, last pushed 2d ago), licensed MIT. It adds 227 tokens to every session and 3,132 once invoked, about $0.0011 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