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 RBraga01/builder-design --skill accessible-ai-outputgit clone --depth 1 https://github.com/RBraga01/builder-designWrote 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/rbraga01/builder-design/accessible-ai-output)<a href="https://agentmods.dev/skills/rbraga01/builder-design/accessible-ai-output"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/accessible-ai-output/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/rbraga01/builder-design/accessible-ai-output"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/accessible-ai-output.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 | $0.00048 | $0.01430 |
| Opus 5 | $0.00024 | $0.00715 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
accessible-ai-output 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 9d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessible AI Output
The Law
AI OUTPUT IS NOT ACCESSIBLE BY DEFAULT.
Streaming text injected into the DOM is invisible to screen readers without ARIA live regions.
"We'll do accessibility later" ships content that is unusable by assistive technology now.
ARIA live regions + reading order + cognitive load review IS accessible AI output.
When to Use
Trigger before:
- Shipping any UI that streams or dynamically renders AI output
- Adding a chat interface, AI response panel, or inline suggestion
- Any component that updates its content in response to a model call
- Rendering structured AI outputs (tables, lists, code blocks generated by a model)
When NOT to Use
- Static content that does not change after initial render
- Server-side rendered pages where the full AI output is in the initial HTML
The Three Accessibility Concerns for AI Output
1 — ARIA Live Regions
Dynamically inserted content is invisible to screen readers unless an aria-live region is declared.
<!-- Streaming output — use polite: screen reader finishes current before announcing -->
<div
role="log"
aria-live="polite"
aria-label="AI response"
aria-atomic="false"
>
<!-- Streamed tokens inserted here -->
</div>
<!-- Error messages — use assertive: interrupts current reading -->
<div role="alert" aria-live="assertive">
Something went wrong. Try again.
</div>
<!-- Status indicators (generating, done) — polite -->
<div aria-live="polite" aria-label="Generation status">
Generating…
</div>
Rules:
aria-live="polite"for response content — does not interrupt what the user is readingaria-live="assertive"for errors only — interrupts; use sparinglyaria-atomic="false"on streaming containers — announces each new chunk, not the entire accumulated textrole="log"for conversational output (chat);role="status"for status messages
2 — Reading Order
Screen readers follow DOM order. Visual layout does not change DOM order.
Common failures in AI UIs:
- User message visually left, AI response visually right — but DOM has AI response before user message
- Floating action buttons (Copy, Retry) placed before the response content in DOM
- Streaming status indicator inserted at the top of the DOM but visually shown below the input
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.
- 9d ago First seen · 162 lines · 48 tokens per session scan A 2cf826328237
accessible-ai-output is a skill published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,430 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…
data-display-and-selection
Complex data deserves multiple view modes — grid, list, table — chosen by the user based on their task. Row and item selection should use large hit areas (the whole row or card, not just a checkbox). Selected state is communicated through a subtle background colour shift. Mass actions appear when items are selected.…
generate-ui-from-brand
Pipeline skill — turns a URL or DESIGN.md into a concrete UI structure with decisions already made. Extracts live design tokens, normalizes them into a semantic system, applies UX principles, and outputs an actionable UI spec. Use when building UI for an existing brand from scratch, auditing a design system, or…