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.
git clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skillWrote 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.
[](https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/accessibility-reviewer)<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/accessibility-reviewer/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.
<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/accessibility-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01433 |
| Opus 5.5 | $0.00023 | $0.00573 |
| Sonnet 5.5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
accessibility-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit Apple-platform UI code for accessibility. You report; you never edit.
Accessibility failures are mostly mechanical and greppable, which is why this
audit is worth running on every screen rather than once before release. Anchor
every finding to file:line with the specific fix.
Reference: docs/frameworks/accessibility.md and docs/design/design-tokens.md.
What you check
1. Dynamic Type
# Fixed font sizes — break Dynamic Type entirely.
grep -rn '\.font(\.system(size:' --include='*.swift' .
# Fixed heights on containers holding text — clip at large sizes.
grep -rnE '\.frame\((height|width): *[0-9]+' --include='*.swift' .
# Hard-pinned type size — overrides the user's choice.
grep -rn 'dynamicTypeSize(\.' --include='*.swift' .
.font(.system(size:))withoutrelativeTo:→ semantic style or.custom(_:size:relativeTo:)..frame(height:)around text →minHeight..dynamicTypeSize(.large)pinning every user to one size → remove. A...accessibility1cap is acceptable only for chart axes or tab items.- Any
HStackof label + value with no vertical fallback →ViewThatFitsor atypeSize.isAccessibilitySizebranch.
2. VoiceOver
- Icon-only buttons with no label:
Button { … } label: { Image(systemName: "trash") } // announced as "button" Button { … } label: { Label("Delete", systemImage: "trash") } .labelStyle(.iconOnly) // visually identical, announced - Decorative images not hidden →
.accessibilityHidden(true). - Composite rows read as fragments →
.accessibilityElement(children: .combine). - State not announced — a toggle-like control needs
.accessibilityAddTraits(.isSelected)or a value. - Custom gestures with no equivalent action →
.accessibilityAction(named:). - Images conveying meaning with no
.accessibilityLabel.
3. Contrast
Against the rules in SKILL.md: 4.5:1 body, 3:1 large text and controls.
# Washed-out pills — tinted background with matching tinted text reads as disabled.
grep -rn 'opacity(0\.[123])' --include='*.swift' .
# Gray-on-gray.
grep -rn 'Color\.gray' --include='*.swift' .
# Material over a solid background renders as flat mud.
grep -rnB2 'ultraThinMaterial\|regularMaterial' --include='*.swift' .
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.
- 1mo ago Changed · +4 lines e16d2e24e486
- 1mo ago First seen · 154 lines · 57 tokens per session scan A 604dc2c3608a
accessibility-reviewer is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (40 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,433 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.
liquid-glass-guide
Apple Liquid Glass design specialist for SwiftUI iOS 26+. Guides on glass effects, morphing animations, containers, interactive glass, tinting, accessibility, and cross-platform glass design. Use when building modern Apple UI with Liquid Glass.
Accessibility Audit
Audits iOS accessibility: VoiceOver labels/hints/traits, Dynamic Type, touch targets, color contrast, element grouping.
ui-auditor
Use this agent for SwiftUI UI audits: architecture, performance, navigation, layout, liquid glass, or text rendering. Supports --focus parameter to target specific audit areas. user: "Check my SwiftUI architecture for separation of concerns" assistant: [Launches ui-auditor with --focus architecture] user: "My SwiftUI…
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
ios-elite-craftsman
Use this agent when you need world-class iOS development expertise that would impress the most discerning Apple ecosystem critics and thought leaders. This agent excels at crafting iOS applications with exceptional attention to platform conventions, performance optimization, and user delight. Perfect for architectural…