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 Community-Access/accessibility-agents --skill kb-mobile-accessibilitygit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/community-access/accessibility-agents/kb-mobile-accessibility)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/kb-mobile-accessibility"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/kb-mobile-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/community-access/accessibility-agents/kb-mobile-accessibility"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/kb-mobile-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 | $0.00052 | $0.03939 |
| Opus 5.5 | $0.00021 | $0.01576 |
| Sonnet 5.5 | $0.00010 | $0.00788 |
| Haiku 4.5 | $0.00005 | $0.00394 |
Grade A, and why
kb-mobile-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 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Accessibility Skill
This skill provides mobile accessibility reference data for React Native, Expo, iOS, and Android auditing. Used by mobile-accessibility.agent.md.
React Native Accessibility Props - Full Reference
Each prop, with its type, values or notes, WCAG SC and required.
| Prop | Type | Values / Notes | WCAG SC | Required |
|---|---|---|---|---|
accessible |
boolean | true marks the view as an accessibility node |
4.1.2 | Conditional |
accessibilityLabel |
string | Human-readable name - overrides all child text | 1.1.1, 4.1.2 | Yes (all interactive + image elements) |
accessibilityLabelledBy |
string / string[] | References ID(s) of labelling element | 1.3.1 | For form inputs |
accessibilityRole |
string (see roles table) | Communicates element type to AT | 4.1.2 | Yes (all interactive elements) |
accessibilityHint |
string | Additional context spoken after label + role | 1.3.3 | When action isn't obvious |
accessibilityState |
object | {checked, disabled, expanded, selected, busy} |
4.1.2 | State-bearing elements |
accessibilityValue |
object | {min, max, now, text} |
1.3.1 | Sliders, steppers, progress bars |
accessibilityActions |
array | [{name, label}] - defines custom actions |
4.1.3 | Context menus, long-press alternatives |
onAccessibilityAction |
function | Handles custom action triggers | 4.1.3 | Paired with accessibilityActions |
accessibilityLiveRegion |
string | 'none' / 'polite' / 'assertive' |
4.1.3 | Dynamic content updates |
accessibilityViewIsModal |
boolean | true traps VoiceOver focus inside modal |
1.3.4 | Modals, drawers, sheets |
accessibilityElementsHidden |
boolean | iOS - hides element and children from VoiceOver | 1.1.1 | Decorative elements |
importantForAccessibility |
string | Android - 'auto' / 'yes' / 'no' / 'no-hide-descendants' |
1.1.1 | Decorative / grouped elements |
accessibilityIgnoresInvertColors |
boolean | iOS - preserves colors in Inverted Colors mode | - | Images, video |
aria-label |
string | RN 0.73+ alias for accessibilityLabel |
1.1.1, 4.1.2 | Preferred in new code |
aria-labelledby |
string | RN 0.73+ alias for accessibilityLabelledBy |
1.3.1 | Form inputs |
aria-describedby |
string | RN 0.73+ alias for accessibilityHint |
1.3.3 | Additional description |
aria-role |
string | RN 0.73+ alias for accessibilityRole |
4.1.2 | All interactive elements |
aria-checked |
boolean / 'mixed' | RN 0.73+ alias for accessibilityState.checked |
4.1.2 | Checkboxes |
aria-disabled |
boolean | RN 0.73+ alias for accessibilityState.disabled |
4.1.2 | Disabled elements |
aria-expanded |
boolean | RN 0.73+ alias for accessibilityState.expanded |
4.1.2 | Accordions, dropdowns |
aria-selected |
boolean | RN 0.73+ alias for accessibilityState.selected |
4.1.2 | Tabs, list items |
aria-busy |
boolean | RN 0.73+ alias for accessibilityState.busy |
4.1.3 | Loading elements |
aria-hidden |
boolean | RN 0.73+ - maps to importantForAccessibility / accessibilityElementsHidden |
1.1.1 | Decorative content |
aria-live |
string | RN 0.73+ alias for accessibilityLiveRegion |
4.1.3 | Dynamic content |
aria-modal |
boolean | RN 0.73+ alias for accessibilityViewIsModal |
1.3.4 | Modals |
What ships with it
1 file 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.
- 1mo ago First seen · 389 lines · 52 tokens per session scan A 10fce3a34393
kb-mobile-accessibility is a skill published in the GitHub repository Community-Access/accessibility-agents (428 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,939 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 2026-09-23.
Other skills, from other repositories
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
Accessibility A11y Enhanced
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.
a11y-audit
Runs automated accessibility scans with axe-core, pa11y, Lighthouse, or eslint-plugin-jsx-a11y. Interprets results, prioritizes violations, and generates fix recommendations. Use when asked to audit, scan, or check accessibility of a page, component, or codebase.
testing-strategy
Guides accessibility testing strategy — what to test automatically vs manually vs with assistive technology. Provides keyboard testing checklists, screen reader testing basics, and acceptance criteria templates. Use when planning testing, writing acceptance criteria, or deciding how to verify accessibility.
automated-a11y-tools
Automated accessibility tooling — Accessibility Scanner (Android), Accessibility Inspector + XCUIAccessibilityAudit (iOS), axe-core Flutter and RN, Espresso a11y checks. Use this to wire a11y checks into CI.
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.