canon-screen-reader

canon-screen-reader is a skill for Claude Code, Codex from Dragoon0x/canon. It costs 63 tokens per session (1,045 once invoked), scanned A, original, MIT.

A guide to making web interfaces work with screen readers such as VoiceOver, NVDA, and JAWS. It focuses on semantic HTML, accessible names, reading order, ARIA roles, states, and announcements.

In plain words
What is it for?
Use it when reviewing headings, buttons, links, landmarks, dialogs, live messages, tables, or other accessibility-tree behavior.
Why use it?
It helps ensure that people who navigate by spoken output can understand the page and operate its controls. It prevents visual layouts from hiding structure or interaction details from assistive technology.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when reviewing headings, buttons, links, landmarks, dialogs, live messages, tables, or other accessibility-tree behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dragoon0x/canon/canon-screen-reader
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 Dragoon0x/canon --skill canon-screen-reader
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/canon

Made for: Claude Code, Codex.

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 canon-screen-reader

README.md
[![agentmods](https://agentmods.dev/badge/skills/dragoon0x/canon/canon-screen-reader/github.svg)](https://agentmods.dev/skills/dragoon0x/canon/canon-screen-reader)
Your own site
<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-screen-reader"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-screen-reader/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 canon-screen-reader

Your own site · 80×15
<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-screen-reader"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-screen-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,045 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 $0.00063 $0.01045
Opus 5.5 $0.00025 $0.00418
Sonnet 5.5 $0.00013 $0.00209
Haiku 4.5 $0.00006 $0.00104

Measured 2mo ago against content hash 38d96e72d329, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

canon-screen-reader 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 2mo 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.

source/skills/canon-screen-reader/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CANON · Screen Reader

Screen readers traverse the accessibility tree, not the visual layout. If the tree is wrong, the interface is wrong for blind and low-vision users.

Semantic HTML first

Screen readers understand HTML elements natively. ARIA is a patch for when HTML can't express the role.

Need Use HTML Not
Button <button> <div role="button">
Link <a href> <span onClick>
Heading <h1>–<h6> <div class="heading">
List <ul>/<ol> <div class="list">
Table <table> with <th> CSS grid of <div>
Landmark <main>, <nav>, <header>, <footer> <div class="nav">
Dialog <dialog> <div class="modal">

Heading hierarchy

Headings create the document outline. Screen reader users navigate by heading. Skip levels or misused headings break this navigation.

  • One <h1> per page.
  • No skipping levels (h1 → h3 without h2).
  • Headings are structure, not styling. Don't use <h3> because you want smaller text; use CSS.

ARIA — only when HTML fails

The first rule of ARIA: don't use ARIA if HTML does the job. The second rule: if you use ARIA, use it correctly and completely.

Common ARIA patterns done right:

<!-- Live region for dynamic updates -->
<div role="status" aria-live="polite">3 results found</div>

<!-- Custom disclosure -->
<button aria-expanded="false" aria-controls="panel">Details</button>
<div id="panel" hidden>...</div>

<!-- Tab interface → see canon-tabs -->

Visually hidden but screen-reader accessible

.sr-only {
  position: absolute;
  width: 1px; height: 1px;
  padding: 0; margin: -1px;
  overflow: hidden;
  clip: rect(0, 0, 0, 0);
  white-space: nowrap;
  border: 0;
}

Use for: labels that are visually implied, skip links before focus, extra context.

Live regions — announce dynamic changes

Role Urgency Use
role="status" / aria-live="polite" Low — waits for pause Search result count, save confirmation
role="alert" / aria-live="assertive" High — interrupts Error messages, time-sensitive warnings

Read the full file on GitHub · 112 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. 2mo ago First seen · 112 lines · 63 tokens per session scan A 38d96e72d329

Subscribe to this mod's changes

canon-screen-reader is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 1,045 once invoked, about $0.0003 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 2026-09-03.

Related

canon-screen-reader compared with skills from other repositories

canon-screen-reader next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
canon-screen-readerDragoon0x/canonSkill66mo agoMITA63Claude Code, Codex
accessibilitydiegosouzapw/awesome-omni-skillsSkill1704mo agoMITC119Claude Code, Codex
accessibilityericrisco/rsc-harnessSkill5032d agoMITA86Claude Code, Codex
accessibility-auditoyi77/1ai-skillsSkill17yesterdayMITA29Claude Code
a11y-auditgreglas75/zuvoSkill73d agoMITA147Claude Code
axe-audittonone-ai/tononeSkill7723d agoMITA47Claude Code
accessibility-compliance-accessibility-audit-v2diegosouzapw/awesome-omni-skillsSkill1704mo agoMITA76Claude Code