accessible-ai-output

accessible-ai-output is a skill for Claude Code from RBraga01/builder-design. It costs 48 tokens per session (1,430 once invoked), scanned A, original, MIT.

Accessibility guidance for interfaces that stream or update AI-generated content. Accessibility means making software usable with tools such as screen readers, including when new text appears on the page.

In plain words
What is it for?
It helps review chat screens, AI response panels, inline suggestions, generated tables, lists, and code blocks before they are shipped.
Why use it?
AI output is added dynamically and can be missed by screen readers or become difficult to follow without attention to announcements, reading order, and cognitive load.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the builder-design plugin — 8 skills, 5 agents shipped together

Good fit It helps review chat screens, AI response panels, inline suggestions, generated tables, lists, and code blocks before they are shipped.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rbraga01/builder-design/accessible-ai-output
Install

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.

Any agent
npx skills add RBraga01/builder-design --skill accessible-ai-output
Clone the repo
git clone --depth 1 https://github.com/RBraga01/builder-design

Made for: Claude Code.

Or install builder-design, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

Wrote 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.

agentmods badge for accessible-ai-output

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbraga01/builder-design/accessible-ai-output/github.svg)](https://agentmods.dev/skills/rbraga01/builder-design/accessible-ai-output)
Your own site
<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.

agentmods 80×15 button for accessible-ai-output

Your own site · 80×15
<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>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 2cf826328237, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/accessible-ai-output/SKILL.md · 162 lines

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 reading
  • aria-live="assertive" for errors only — interrupts; use sparingly
  • aria-atomic="false" on streaming containers — announces each new chunk, not the entire accumulated text
  • role="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

Read the full file on GitHub · 162 lines

Changes

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.

  1. 9d ago First seen · 162 lines · 48 tokens per session scan A 2cf826328237

Subscribe to this mod's changes

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.

Related

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…

nateherkai/scroll-craft · 177 tokens

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".

addyosmani/web-quality-skills · 51 tokens

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.

AnastasiyaW/codex-claude-code-config · 264 tokens

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…

dembrandt/dembrandt-skills · 68 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.…

dembrandt/dembrandt-skills · 85 tokens

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…

dembrandt/dembrandt-skills · 72 tokens