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 rshankras/claude-code-apple-skills --skill accessibility-auditgit clone --depth 1 https://github.com/rshankras/claude-code-apple-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/rshankras/claude-code-apple-skills/accessibility-audit)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/accessibility-audit/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/rshankras/claude-code-apple-skills/accessibility-audit"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/accessibility-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00060 | $0.01412 |
| Opus 5 | $0.00030 | $0.00706 |
| Sonnet 5 | $0.00012 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
accessibility-audit 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit
A repeatable audit workflow that takes an app from "we think it's accessible" to evidence: automated audits in CI, an Inspector pass, manual assistive-tech passes, and an Accessibility Nutrition Label evaluation you can defend. Distilled from Apple's WWDC23 "Perform accessibility audits" (10035), WWDC19 "Accessibility Inspector" (257), WWDC25 "Evaluate your app for Accessibility Nutrition Labels" (224), and the 2026 Tech Talk "Prepare your app for Accessibility Nutrition Labels" (111433).
Why it matters: Accessibility Nutrition Labels on the App Store make your support (or its absence) visible before download.
When This Skill Activates
- User asks for an accessibility audit, review, or compliance check
- User is preparing Accessibility Nutrition Label declarations for App Store Connect
- User asks about
performAccessibilityAudit, Accessibility Inspector, or automated a11y testing - User mentions EU Accessibility Act / accessibility compliance
- Pre-release checks (pairs with
release-review)
The Audit Workflow
1. Define common tasks first (WWDC25 224)
List the primary tasks people download the app for, plus the fundamentals: first-launch experience, login, purchase, settings. Every subsequent pass evaluates these tasks, on every device family the app supports.
2. Automated pass — XCUITest audits in CI
try app.performAccessibilityAudit() audits the current view exactly as the Inspector does; the test fails automatically on findings. Full API, audit-type table, issue filtering, and CI patterns: automated-audits.md. Baseline rules:
- Audits cover only what's on screen — write one audit per distinct screen/state.
continueAfterFailure = truebefore the audit to surface all issues in one run.- Filter accepted issues via the issue handler — never by skipping whole audit types.
3. Inspector pass (WWDC19 257)
Xcode → Open Developer Tool → Accessibility Inspector, target the app:
- Run Audit → each finding highlights the view and offers a Help suggestion.
- Fix, re-run to zero.
- Auto Navigate through the screen with the speaker button — hear exactly what VoiceOver would say, in order; wrong reading order shows up here.
- Point Inspection for spot checks; Color Contrast Calculator (Window menu) for failing pairs.
What ships with it
2 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.
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.
- 6d ago First seen · 92 lines · 60 tokens per session scan A 5148f8603e26
accessibility-audit is a skill published in the GitHub repository rshankras/claude-code-apple-skills (710 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,412 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ios-screenshot-taker
Use when capturing deterministic iOS simulator screenshots for App Store, TestFlight, QA, launch pages, or marketing decks. Covers xcodebuild build, simulator boot/install/launch, seeded demo states, xcrun simctl screenshots, required App Store device classes, public-safe output handling, and slash commands such as…
ui-crawler-max
Autonomous UI crawler for iOS simulator apps — rapid, element-precise data collection. Use whenever the user says "crawl my app", "auto-test the UI", "click/tap through every screen", "monkey test", "explore the app and find errors/crashes", "collect screenshots of all screens", "smoke test the whole app", or asks for…
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.