liquid-glass-auditor

liquid-glass-auditor is an agent for Claude Code from CharlesWiltgen/Axiom. It costs 163 tokens per session (4,999 once invoked), scanned A, original, MIT.

A code-review agent for SwiftUI apps, focused on Liquid Glass, Apple’s newer translucent interface style in iOS 26 and later. It scans the codebase for places where this style could be added or improved.

In plain words
What is it for?
Use it to review SwiftUI views, toolbars, blur-effect migrations, tinting, and compatibility checks before adopting Liquid Glass.
Why use it?
It shows where Liquid Glass is missing, incorrectly configured, or likely to look visually muddled, including on older iOS versions.

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 Use it to review SwiftUI views, toolbars, blur-effect migrations, tinting, and compatibility checks before adopting Liquid Glass.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charleswiltgen/axiom/liquid-glass-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 liquid-glass-auditor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/liquid-glass-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/liquid-glass-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,999 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 $0.00163 $0.04999
Opus 5 $0.00081 $0.02499
Sonnet 5 $0.00033 $0.01000
Haiku 4.5 $0.00016 $0.00500

Measured 11d ago against content hash 021cc09a18ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

liquid-glass-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/liquid-glass-auditor.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Liquid Glass Auditor Agent

You are an expert at identifying Liquid Glass adoption opportunities AND adoption gaps — both surfaces where the iOS 26+ visual treatment isn't yet applied AND adoption-completeness issues like ungated effects on older OS, wrong variant for content type (Regular vs Clear), nested glass causing visual muddiness, and missing tint discipline on primary actions.

Note on Audit Framing

Unlike safety-oriented auditors, this agent surfaces adoption opportunities, not bugs. A codebase with no Liquid Glass adoption is not broken — it's pre-adoption. The Health Score reflects adoption progress (NOT ADOPTED → PARTIAL → ADOPTED), and "issues" are framed as opportunities with priority by impact, not danger.

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 Visual Treatment Architecture

Step 1: Identify Deployment Target and Availability Discipline

Glob: **/*.swift, **/*.xcconfig, **/Info.plist
Grep for:
  - `IPHONEOS_DEPLOYMENT_TARGET`, `MACOSX_DEPLOYMENT_TARGET` — deployment target
  - `if #available\(iOS\s+26`, `if #available\(macOS\s+15`, `if #available\(macOS\s+26` — availability gates for Liquid Glass
  - `@available\(iOS\s+26`, `@available\(macOS\s+26` — type/method-level availability

Step 2: Identify Existing Visual Effects (Migration Surface)

Grep for:
  - `UIBlurEffect`, `UIVisualEffectView` — UIKit blur (legacy)
  - `NSVisualEffectView` — AppKit blur (legacy)
  - `\.ultraThinMaterial`, `\.thinMaterial`, `\.regularMaterial`, `\.thickMaterial`, `\.ultraThickMaterial`, `\.bar` — SwiftUI Material (legacy on iOS 26+)
  - `\.background\(\.material`, `\.background\(\.regularMaterial` — Material as background
  - `\.blur\(radius:` — explicit blur (intentional or migration candidate)
  - `\.background\(\.ultraThin` — material backgrounds

Read the full file on GitHub · 335 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 · 335 lines · 163 tokens per session scan A 021cc09a18ad

Subscribe to this mod's changes

liquid-glass-auditor is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,155 stars, last pushed 2d ago), licensed MIT. It adds 163 tokens to every session and 4,999 once invoked, about $0.0008 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

reviewer-accessibility

Multi-perspective accessibility reviewer. Scans changed files for missing ARIA attributes, color-only state signals, keyboard navigation gaps, and CLI ANSI-color-only output differentiation. Returns SKIP when no UI changes are present (checked against the authoritative UI file pattern list in verdict-schema.md §2.3…

Jamie-BitFlight/claude_skills · 106 tokens

review-ui-blazor

UI/Blazor reviewer for Razor components. Checks accessibility, culture-dependent rendering, CSS correctness, component lifecycle, and Blazor-specific pitfalls. Returns PASS or FAIL with specific findings. Only runs when .razor files are changed.

dodobrands/ai-hub · 53 tokens

ui-interaction-reviewer

Interactive-component review — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. Checks the invisible details that compound into "feels right": :active states, spatial-consistency entry/exit, modal vs popover transform-origin, inline form errors, focus-visible, optimistic UI…

RaNDoM6913/claude-code-superkit · 208 tokens

ui-motion-reviewer

Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…

RaNDoM6913/claude-code-superkit · 189 tokens

ui-typography-reviewer

Typography-specific deep review — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType features, web-font loading. Dispatch when a font-family, font-weight, or type-scale token changed; when a Google Fonts or font-loading import was added or changed; when the user asks about fonts…

RaNDoM6913/claude-code-superkit · 129 tokens

cosmo

Cosmo - CSS Consistency Reviewer for web application styling.

sam-agents/sam · 11 tokens