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.
npx skills add rusel95/ios-agent-skills --skill ios-accessibilitygit clone --depth 1 https://github.com/rusel95/ios-agent-skillsWrote 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/skills/rusel95/ios-agent-skills/ios-accessibility)<a href="https://agentmods.dev/skills/rusel95/ios-agent-skills/ios-accessibility"><img src="https://agentmods.dev/badge/skills/rusel95/ios-agent-skills/ios-accessibility/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/skills/rusel95/ios-agent-skills/ios-accessibility"><img src="https://agentmods.dev/badge/skills/rusel95/ios-agent-skills/ios-accessibility.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 | $0.00253 | $0.06268 |
| Opus 5 | $0.00127 | $0.03134 |
| Sonnet 5 | $0.00051 | $0.01254 |
| Haiku 4.5 | $0.00025 | $0.00627 |
Grade A, and why
ios-accessibility 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 9d 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Accessibility
Production-grade accessibility skill for iOS codebases aligned with WCAG 2.2 AA and Apple Human Interface Guidelines. Operates correction-first — AI coding assistants (including Claude) systematically generate inaccessible iOS code because most training data lacks accessibility. This skill intercepts those patterns and enforces accessible output from the start.
The skill covers both SwiftUI and UIKit with framework-appropriate patterns, and produces code that works across VoiceOver, Switch Control, Voice Control, Full Keyboard Access, and Dynamic Type.
Why This Skill Exists
Research (CodeA11y, arXiv 2502.10884) found that AI omits accessibility because: (1) developers don't prompt for it so AI doesn't provide it, (2) most training code is inaccessible, and (3) generated code omits manual steps like replacing placeholder labels. This skill ensures every code generation pass includes accessibility from the start — not as an afterthought.
Quick Decision Trees
Which framework's patterns apply?
Is the file SwiftUI (.swift with View conformance)?
├── YES → Apply SwiftUI patterns → Read references/swiftui-patterns.md
└── NO → Is the file UIKit (.swift with UIView/UIViewController)?
├── YES → Apply UIKit patterns → Read references/uikit-patterns.md
└── NO → Mixed — apply BOTH checklists per file type
Is this element interactive?
Can the user tap/activate this element?
├── YES → Is it using Button, Toggle, Slider, Picker, or Link?
│ ├── YES → Standard control — verify accessibilityLabel exists
│ └── NO → Using onTapGesture or custom view?
│ └── 🔴 REPLACE with Button or appropriate standard control
│ onTapGesture is invisible to VoiceOver, Switch Control, and eye tracking
└── NO → Is it a meaningful image or icon?
├── YES → Add accessibilityLabel describing content, not appearance
└── NO → Decorative → Image(decorative:) or .accessibilityHidden(true)
Does this text support Dynamic Type?
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 8.6 KB
- references/ai-failure-patterns.md 10 KB
- references/color-visual.md 4.7 KB
- references/compliance.md 3.8 KB
- references/dynamic-type.md 6.2 KB
- references/ios-new-features.md 4.1 KB
- references/motion-input.md 5.3 KB
- references/rules.md 5.1 KB
- references/swiftui-patterns.md 8.7 KB
- references/testing.md 6.2 KB
- references/uikit-patterns.md 5.5 KB
- references/voiceover-patterns.md 11 KB
- references/wcag-ios-mapping.md 5.2 KB
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.
- 9d ago First seen · 386 lines · 253 tokens per session scan A 43017b2e222c
ios-accessibility is a skill published in the GitHub repository rusel95/ios-agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 253 tokens to every session and 6,268 once invoked, about $0.0013 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.
Other skills, from other repositories
apple-hig-ux
Apple-platform design and UX judgment — what a good iOS/iPadOS/macOS/watchOS/visionOS app FEELS like. Use whenever designing app screens or flows, answering Human Interface Guidelines (HIG) questions, judging "does this feel native", running a UX review of an Apple-platform app, choosing navigation patterns (tabs vs…
ui-ios
Generate slop-free SwiftUI UI for iOS 17+ (iPhone and iPad). Use whenever the user asks to build, design, scaffold, restyle, or improve a SwiftUI screen, View, sheet, NavigationStack, tab, or any iOS interface. Greenfield mobile coverage — does not replace any existing skill. Two phases — tokens first (with approval…
ios-accessibility
Never use generic labels like "button", "image", or "icon". Describe what it does: "Delete message", "Add to favorites", "Share photo".
human-interface-guidelines
Route Human Interface Guidelines (Foundations) design tasks to the correct Knowledge Contracts — layout, color, typography, dark mode, materials, motion, app icons, interface icons, images, branding, accessibility design, inclusion, privacy-design permission UI, SF Symbols usage, and right-to-left support. Use when…
human-interface-guidelines-components
Route Human Interface Guidelines Components/Inputs design tasks to the correct Knowledge Contracts -- lists and tables, buttons, sheets, alerts, action sheets, navigation bars, tab bars, pickers, toggles, text fields, menus, and touchscreen gestures. Use when designing or reviewing iOS/iPadOS list/table layout, button…
human-interface-guidelines-patterns
Route Human Interface Guidelines Patterns design tasks to the correct Knowledge Contracts -- onboarding, searching, settings, notifications, feedback, and undo/redo. Use when designing or reviewing an iOS/iPadOS first-run flow, in-app search placement, settings-screen structure, notification content/timing…