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-keyboardgit 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-keyboard)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-keyboard"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-keyboard/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-keyboard"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-keyboard.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 | $0.00070 | $0.00874 |
| Opus 5.5 | $0.00028 | $0.00350 |
| Sonnet 5.5 | $0.00014 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
canon-keyboard 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Keyboard
If it doesn't work with a keyboard, it doesn't work. Period.
Tab order = visual order
Tab moves focus through interactive elements in document order. That order must match the visual layout. If CSS rearranges elements visually (flexbox order, grid placement, position: absolute), the tab order still follows DOM order. Fix the DOM, not the visual.
Never use tabindex > 0. It forces elements to the front of tab order globally and breaks the natural flow.
| tabindex value | Meaning |
|---|---|
| 0 | Focusable in natural order |
| -1 | Focusable only via JS (.focus()), not via Tab |
| > 0 | Never use. Forces unnatural order. |
Interactive elements are natively focusable
<button>, <a href>, <input>, <select>, <textarea> — all keyboard-accessible by default. If you're adding tabindex="0" and onKeyDown to a <div>, you've reinvented a button badly.
Composite widgets — arrow keys, not Tab
Inside a toolbar, tab bar, radio group, or menu, arrow keys move between items. Tab enters and exits the group. This is the roving tabindex or aria-activedescendant pattern.
| Widget | Internal navigation |
|---|---|
| Tabs | Arrow Left/Right (horizontal), Up/Down (vertical) |
| Menu | Arrow Up/Down, Enter to activate, Escape to close |
| Toolbar | Arrow Left/Right between buttons |
| Radio group | Arrow Up/Down or Left/Right |
| Tree view | Arrow Up/Down to traverse, Right to expand, Left to collapse |
Keyboard shortcuts
- Document them. An undiscoverable shortcut is a non-shortcut.
- Use
⌘/Ctrl + letterfor common actions (⌘S save, ⌘K command palette). - Don't override browser shortcuts (⌘L address bar, ⌘T new tab, ⌘W close tab).
- Use single-key shortcuts (like
?for help) only in apps, not content pages (WCAG 2.1.4). - Allow users to remap or disable shortcuts.
Focus indicators
See canon-focus for visual specs. Key rule: every focused element must be visually distinguishable. outline: none without a replacement is an accessibility violation.
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 · 77 lines · 70 tokens per session scan A 3f06edc38a63
canon-keyboard is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 70 tokens to every session and 874 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 2026-08-31.
canon-keyboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-keyboardDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 70 | 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 |