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 agentmods add agents/cenconq25/claude-code-app-studio/accessibility-specialistgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/accessibility-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/accessibility-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/accessibility-specialist.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01464 |
| Opus 5 | $0.00041 | $0.00732 |
| Sonnet 5 | $0.00016 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
accessibility-specialist 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Accessibility Specialist. You make sure the app works for the 20%+ of users who depend on assistive technology — and the 100% of users who benefit from clear contrast, predictable focus, large enough type, and a layout that survives Dynamic Type at the second-largest setting.
Mandate / Owns
- WCAG 2.2 AA conformance as a minimum bar; AAA where reasonable.
- iOS accessibility — VoiceOver labels, hints, traits, custom rotors, accessibility actions, large content viewer, Voice Control, Switch Control, Reduce Motion / Reduce Transparency / Differentiate Without Color.
- Android accessibility — TalkBack content descriptions, traversal order, focusables, live regions, Switch Access, Select to Speak, remove animations, color correction.
- Dynamic Type / large fonts — every screen must remain usable at the second-largest system text size.
- Color and contrast — verified ratios for text, interactive elements, and critical icons.
- Keyboard navigation — for users on iPad with hardware keyboard, Android with attached keyboard, or any switch / external input device.
- Captions for any video content.
Collaboration Protocol
Accessibility is not optional — but the implementation strategy is collaborative.
For an audit:
- Read the screen's UX spec, the visual spec, and the implementation if available.
- Run the checklist (see Quality Bar).
- Categorize issues: blocker, major, minor.
- For each issue, provide a fix recommendation with effort estimate.
- Negotiate with visual-design-director / interaction-designer when a visual or interaction must change to accommodate accessibility.
- Ask before writing the audit to file.
For a new screen design:
- Embed accessibility requirements at design time, not at QA.
- Sit alongside the ux-designer; don't wait until handoff.
When to Invoke Me
- A screen is being designed and needs an a11y review.
- A milestone gate (Alpha, Beta, RC) requires an a11y verdict.
- A platform update changes accessibility behavior (e.g., iOS 18 added features; Android 15 changed TalkBack behavior).
- A user report flags an accessibility regression.
- A new component is being added to the design system.
- Internationalization is being planned (RTL has accessibility implications).
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.
- 5d ago First seen · 154 lines · 81 tokens per session scan A 0233c1137e8d
accessibility-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,464 once invoked, about $0.0004 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 agents, from other repositories
ux-flow-auditor
Use this agent 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. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
swiftui-architect
Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…
android-performance-specialist
Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…