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 dadederk/iOS-Accessibility-Agent-Skill --skill ios-accessibilitygit clone --depth 1 https://github.com/dadederk/iOS-Accessibility-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/skills/dadederk/ios-accessibility-agent-skill/ios-accessibility)<a href="https://agentmods.dev/skills/dadederk/ios-accessibility-agent-skill/ios-accessibility"><img src="https://agentmods.dev/badge/skills/dadederk/ios-accessibility-agent-skill/ios-accessibility.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00101 | $0.02065 |
| Opus 5 | $0.00051 | $0.01033 |
| Sonnet 5 | $0.00020 | $0.00413 |
| Haiku 4.5 | $0.00010 | $0.00206 |
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 7d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Accessibility
Overview
This skill provides expert guidance on iOS accessibility, covering VoiceOver, Dynamic Type, assistive technologies, inclusive design practices, and both UIKit and SwiftUI implementations. Use this skill to help developers build apps that work for everyone.
The Approach
- Shift-left — Accessibility is part of the process. It needs to be considered even in prototypes or MVPs.
- User-centric — Accessibility is about people. Checklists help, but the goal is not checklist compliance. The goal is to offer a great experience for users with disabilities.
- Progress over perfection — Anytime is a good time to start. Focus on iterative and incremental improvements as you go. It goes a long way.
- Test as you go — Manual testing is part of development.
Agent Behavior Contract
- Accessibility is non-deterministic. Propose potential solutions in order of confidence and present with clear pros, cons, and trade-offs.
- Before proposing fixes, identify the platform (UIKit vs SwiftUI) and the assistive technology, accessibility feature, or design consideration in context.
- Do not recommend accessibility fixes without considering the user experience impact.
- Prefer manual testing guidance alongside code changes, together with any automated or semi-automated solutions.
- Cross-reference multiple assistive technologies when relevant (VoiceOver, Voice Control, Switch Control, Full Keyboard Access).
Anti-Patterns to Avoid
- Do not add trait names to labels — Say "Close", not "Close button" (VoiceOver adds "button" automatically, when using the button trait)
- Do not use
.accessibilityHidden(true)on interactive elements — Users won't be able to access them - Do not use fixed font sizes — Always use text styles for Dynamic Type support
- Do not use hardcoded colors for text — Use semantic colors (
.label,.secondaryLabel) for contrast and Dark Mode - Do not group UIKit elements without a clear combined label — If
isAccessibilityElement = true, setaccessibilityLabel(and value/traits as needed). - Do not group SwiftUI elements without a clear combined label — If
.accessibilityElement(children: .ignore)is used, provide label/value/traits manually. - Do not add hints unless needed — It should be clear what a component expresses, and does, by its label/value/traits. Only configure for adding extra clarity or context.
- Do not rely on
onTapGesturealone — Prefer semantic controls likeButton. If gesture handling is unavoidable, add button traits and clear labels. - Do not scale chrome controls with Dynamic Type — For navigation bars, toolbars, and tab bars, prefer Large Content Viewer (iOS 13+) using
.accessibilityShowsLargeContentViewer/UILargeContentViewerItem.
What ships with it
18 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.
- agents/openai.yaml 299 B
- LICENSE.txt 1.1 KB
- references/concepts-and-culture.md 11 KB
- references/dynamic-type-swiftui.md 14 KB
- references/dynamic-type-uikit.md 12 KB
- references/dynamic-type.md 2.8 KB
- references/full-keyboard-access.md 3.6 KB
- references/glossary.md 8.6 KB
- references/good-practices.md 18 KB
- references/playbook.md 21 KB
- references/resources.md 4.4 KB
- references/switch-control.md 4.2 KB
- references/testing-automated.md 5.5 KB
- references/testing-manual.md 8.2 KB
- references/voice-control.md 3.6 KB
- references/voiceover-swiftui.md 17 KB
- references/voiceover-uikit.md 26 KB
- references/voiceover.md 5.9 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.
- 7d ago First seen · 139 lines · 101 tokens per session scan A 5a393f8c79a3
ios-accessibility is a skill published in the GitHub repository dadederk/iOS-Accessibility-Agent-Skill (167 stars, last pushed 6mo ago), licensed MIT. It adds 101 tokens to every session and 2,065 once invoked, about $0.0005 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.
Other skills, from other repositories
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an…
expo-design-system
Framework (OSS). Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when…
flutter-build-responsive-layout
Use LayoutBuilder, MediaQuery, or Expanded/Flexible to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.
omh-apple-design
This is a Hermes-native apple-design workflow skill.
axiom-audit-liquid-glass
Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.
axiom-audit-ux-flow
Use when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.