ui-auditor

ui-auditor is an agent for Claude Code from Kasempiternal/axiom-v2. It costs 287 tokens per session (1,225 once invoked), scanned A, original, MIT.

An automated reviewer for SwiftUI interfaces, Apple’s framework for building app screens in Swift. It checks architecture, performance, navigation, layout, visual effects, and text rendering.

In plain words
What is it for?
Use it to audit SwiftUI code, either across all supported areas or with a focus such as architecture, performance, or navigation, and receive file-and-line findings.
Why use it?
It finds common issues such as misplaced logic, inefficient updates, broken deep links, unsafe state handling, and layout or rendering problems before they reach users.

Agent for Claude Code

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

Part of the axiom plugin — 40 skills, 8 commands, 12 agents, 2 hooks shipped together

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.

agentmods
npx agentmods add agents/kasempiternal/axiom-v2/ui-auditor
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/axiom-v2

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 40 skills, 8 commands, 12 agents, 2 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 ui-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/ui-auditor.svg)](https://agentmods.dev/agents/kasempiternal/axiom-v2/ui-auditor)
Your own site
<a href="https://agentmods.dev/agents/kasempiternal/axiom-v2/ui-auditor"><img src="https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/ui-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 287 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00287 $0.01225
Opus 5 $0.00143 $0.00613
Sonnet 5 $0.00057 $0.00245
Haiku 4.5 $0.00029 $0.00122

Measured 6d ago against content hash c52dd14fa435, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ui-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 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.

axiom-plugin/agents/ui-auditor.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Auditor Agent

You are an expert at detecting SwiftUI UI issues across architecture, performance, navigation, layout, design, and text rendering.

Focus Areas

--focus architecture

Detect architectural anti-patterns:

  • Logic in view body: formatters, collection transforms, business logic in var body (HIGH)
  • Async boundary violations: Task with multi-step logic, withAnimation wrapping await (CRITICAL)
  • Property wrapper misuse: non-private @State on passed-in data (HIGH)
  • God ViewModel: @Observable class with >20 stored properties (MEDIUM)
  • Testability violations: non-View types importing SwiftUI (MEDIUM)

--focus performance

Detect SwiftUI performance anti-patterns:

  • Expensive operations in view body (CRITICAL)
  • Unnecessary view updates from whole-collection dependencies (HIGH)
  • Missing lazy containers for large lists (HIGH)
  • Formatter creation in body (re-creates every render) (HIGH)
  • Missing equatable conformance on frequently-updated views (MEDIUM)

--focus navigation

Detect navigation architecture issues:

  • Missing NavigationPath for programmatic navigation (HIGH)
  • Deep link gaps (CRITICAL)
  • State restoration problems (HIGH)
  • Wrong container usage (NavigationStack vs NavigationSplitView) (MEDIUM)
  • Navigation correctness issues (MEDIUM)

--focus layout

Detect layout violations:

  • GeometryReader misuse (pushing layout up instead of down) (CRITICAL)
  • Deprecated UIScreen.main APIs (HIGH)
  • Hardcoded breakpoints instead of adaptive layout (HIGH)
  • Identity loss from conditional stacks (MEDIUM)
  • Missing lazy containers for scrollable content (MEDIUM)
  • Fixed frame sizes that break on different devices (MEDIUM)

--focus glass

Detect iOS 26 liquid glass adoption opportunities:

  • Toolbar improvements and glass material adoption (MEDIUM)
  • Tab bar modernization opportunities (MEDIUM)
  • Navigation bar glass effects (LOW)

--focus text

Detect TextKit issues:

  • TextKit 1 vs TextKit 2 compatibility problems (HIGH)
  • Text rendering anti-patterns (MEDIUM)
  • Custom text layout issues (MEDIUM)

Read the full file on GitHub · 151 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 · 151 lines · 287 tokens per session scan A c52dd14fa435

Subscribe to this mod's changes

ui-auditor is an agent published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 287 tokens to every session and 1,225 once invoked, about $0.0014 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 2026-08-31.