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 Dragoon0x/canon --skill canon-screen-readergit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/dragoon0x/canon/canon-screen-reader)<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.
<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>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 | $0.00063 | $0.01045 |
| Opus 5.5 | $0.00025 | $0.00418 |
| Sonnet 5.5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00104 |
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.
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 |
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.
- 2mo ago First seen · 112 lines · 63 tokens per session scan A 38d96e72d329
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.
canon-screen-reader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-screen-readerDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 63 | Claude Code, Codex |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| accessibility-auditoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |
| a11y-auditgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 147 | Claude Code |
| axe-audittonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 47 | Claude Code |
| accessibility-compliance-accessibility-audit-v2diegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | A | 76 | Claude Code |