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 kelvinkosbab/AppBootstrapAI --skill android-accessibility-progit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/kelvinkosbab/appbootstrapai/android-accessibility-pro)<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-accessibility-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-accessibility-pro/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/kelvinkosbab/appbootstrapai/android-accessibility-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-accessibility-pro.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 | $0.00092 | $0.01100 |
| Opus 5.5 | $0.00037 | $0.00440 |
| Sonnet 5.5 | $0.00018 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
android-accessibility-pro 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Android app accessibility for correctness and completeness. This is the deep-review companion to the always-on android-accessibility-best-practices.md rule — the rule steers while writing; this skill audits whole screens. The Android sibling of swift-accessibility-pro. Report only genuine problems; don't nitpick.
Applies to Jetpack Compose (primary) with View-interop notes. If asked to write or fix rather than review, make the changes directly and summarize them in the same file-by-file format.
Review process:
- Audit the TalkBack semantics tree using
references/semantics.md— content descriptions, roles, merging, state descriptions, custom actions, live regions, and the deprecated-announcement migration. - Audit Bluetooth assistive input using
references/input-access.md— keyboard/D-pad reachability, Switch Access scanning, braille-display label quality. - Audit visual accessibility using
references/visual.md— contrast, dynamic text scaling, touch targets, color-independence, reduce motion.
If doing a partial review, load only the relevant reference files.
Core Instructions
- Audit the semantics tree, not the code style. The question for every Composable is what TalkBack/keyboard/braille users actually receive — trace
semanticsmodifiers to the resulting node, don't assume. - The input methods share one tree. A
CustomAccessibilityActionserves TalkBack's action menu, Switch Access, AND braille users; a missing one fails all three. Report tree problems once, noting every affected input method. - Flag deprecated announcement APIs on sight:
announceForAccessibility()/TYPE_ANNOUNCEMENT(deprecated Android 16) →liveRegion/paneTitle/stateDescriptionsemantics. AI-generated code still emits the old calls. - Localization is part of accessibility. Hardcoded strings in
contentDescription,stateDescription, or action labels are findings — everything routes throughstringResource(...). - Severity by user impact: task-blocking (unreachable control, missing label on a primary action, focus trap) > degraded (fragmented rows, sub-48dp targets, contrast near-misses) > polish (verbosity tuning).
- Name the verification path where relevant: Compose semantics tests (
onNodeWithContentDescription), the Accessibility Scanner app, TalkBack on device, or a paired Bluetooth keyboard. - Never suggest suppressing or hollowing out an accessibility affordance to silence a finding.
What ships with it
3 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.
- 1mo ago First seen · 74 lines · 92 tokens per session scan A 421317d9a4cb
android-accessibility-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (8 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 1,100 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
kmp-glassmorphism-ui
Implements a production-grade Glassmorphism design system for Kotlin Multiplatform (KMP) Compose Multiplatform projects. Use when the user asks for glass UI, frosted glass effects, glassmorphism theme, translucent/transparent UI components, liquid/blob animated backgrounds, or premium modern dark-mode design in a…
figma-a11y-annotations
Rules for generating accessibility annotations on iOS/iPadOS mobile designs in Figma. Enforces a bare-minimum annotation discipline, an iOS vocabulary instead of web ARIA terms, and exact grammar for names, control types, page titles, values, hints, headings, groups, and reading order. Never annotates visible text as…
iOS SwiftUI Accessibility
Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 24 WCAG criteria.
compose-component-design
Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.
maui-accessibility
Improve MAUI accessibility. USE FOR: semantic labels, hints, headings, screen-reader focus/announcements, AutomationProperties, touch targets, decorative content, TalkBack/VoiceOver/Narrator checks. DO NOT USE FOR: general layout, automation-only tests, performance.
compose-visuals-footguns
Compose look-and-feel traps: theme and colour tokens, artwork palettes, gradients and scrims, shimmer, glass and particle effects, animation, image loading, charts and stats displays (percent changes, shares, buckets). Use when a visual bands, pops, freezes or misleads.