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.
git clone --depth 1 https://github.com/baijum/ukulele-companionWrote 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/rules/baijum/ukulele-companion/compose-accessibility)<a href="https://agentmods.dev/rules/baijum/ukulele-companion/compose-accessibility"><img src="https://agentmods.dev/badge/rules/baijum/ukulele-companion/compose-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/rules/baijum/ukulele-companion/compose-accessibility"><img src="https://agentmods.dev/badge/rules/baijum/ukulele-companion/compose-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 | $0.00000 | $0.00801 |
| Opus 5.5 | $0.00000 | $0.00320 |
| Sonnet 5.5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
compose-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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Accessibility Rules
A core user base relies on TalkBack. Every UI change must preserve and improve accessibility. Breaking accessibility is treated as seriously as breaking functionality.
Rule 1: Icons need contentDescription
Interactive/informative icons MUST have a descriptive contentDescription. Decorative-only icons (inside a labeled button where text suffices) may use null. Use conditional descriptions for toggle states.
Icon(
imageVector = if (isPlaying) Icons.Filled.Stop else Icons.Filled.PlayArrow,
contentDescription = if (isPlaying) "Stop" else "Play"
)
Rule 2: Headings and navigation semantics
Screen titles and section headers MUST have Modifier.semantics { heading() }. Navigation containers should use Modifier.semantics { role = Role.Navigation }.
Text("Tuner", style = MaterialTheme.typography.titleLarge,
modifier = Modifier.semantics { heading() })
Rule 3: Canvas needs text alternatives
Any Canvas conveying information MUST use clearAndSetSemantics with a data-driven description.
Canvas(modifier = Modifier.fillMaxWidth().height(200.dp)
.clearAndSetSemantics { contentDescription = "Tuning meter, 5 cents sharp" }
) { /* drawing */ }
Rule 4: Dynamic content needs live regions
Use LiveRegionMode.Polite for frequent updates (pitch, cents). Use LiveRegionMode.Assertive for important state changes (in tune, correct answer, error).
Text(detectedNote, modifier = Modifier.semantics {
liveRegion = LiveRegionMode.Polite
})
Rule 5: Interactive elements must be focusable and described
Clickable composables need a content description or visible label. Custom interactive components must include role = Role.Button. Reflect state changes in stateDescription.
Box(modifier = Modifier.clickable { onFretTap(string, fret) }.semantics {
contentDescription = "$stringName string, fret $fretNumber, $noteName"
role = Role.Button
if (isSelected) stateDescription = "selected"
})
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 · 89 lines · 0 tokens per session scan A d023255202ba
compose-accessibility is a cursor rule published in the GitHub repository baijum/ukulele-companion (14 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 801 tokens. 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 cursor rules, from other repositories
project
Redface 2 project rules — imports AGENTS.md as source of truth.
project-status
PriceGrab shipped state and product backlog (read first).
android-mobile-frontend-design
Design Android mobile frontend experiences from scratch, improve existing screens, and fix UI issues with brand-forward, localization-safe, overflow-safe guidance across Compose and Views.
android-compose-accessibility
Make Compose interfaces accessible with semantics, announcements, contrast, focus order, and adaptive touch targets.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.