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-interactiongit 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-interaction)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-interaction"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-interaction/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-interaction"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-interaction.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 | $0.00066 | $0.02399 |
| Opus 5.5 | $0.00026 | $0.00960 |
| Sonnet 5.5 | $0.00013 | $0.00480 |
| Haiku 4.5 | $0.00007 | $0.00240 |
Grade A, and why
canon-interaction 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Interaction Design
Every interactive element has 6 visual states. Most AI-generated UIs ship 1 or 2. The states below are the contract between the user and the interface.
The Six States
Every button, link, input, and control must have:
| State | Trigger | Visual change |
|---|---|---|
| Default | Idle | Base appearance |
| Hover | Pointer over (desktop only) | Slight elevation, color shift, or underline |
| Focus | Keyboard tab or click | Ring (2–3px) outside the element |
| Active | Pressed but not released | Slight scale-down or color darken |
| Disabled | Cannot interact | 50% opacity OR muted color, no pointer events |
| Loading | In-flight | Spinner, skeleton, or progress |
For inputs, add a 7th: Error. For toggles, add Selected.
Focus Rings (WCAG 2.4.7, 2.4.13)
:focus-visible {
outline: 2px solid var(--color-focus);
outline-offset: 2px;
}
/* Never remove focus without replacement */
:focus { outline: none; } /* alone: WCAG violation */
:focus-visible { outline: 2px solid; } /* together: OK */
| Property | Value | Source |
|---|---|---|
| Ring width | 2–3px | Visible at all zoom levels |
| Ring offset | 2px | Separates ring from element |
| Ring color | Brand accent or --color-focus |
Must hit 3:1 against adjacent surface |
| Ring style | solid |
dotted/dashed are harder to see |
Use :focus-visible, not :focus. This shows the ring for keyboard users but suppresses it for mouse clicks, which feels right.
Hover
| Element | Hover treatment |
|---|---|
| Button | Background color one step darker (-4 to -8% L) |
| Link (text) | Underline appears OR color one step darker |
| Card (clickable) | Subtle elevation (shadow + 1–2px translateY) |
| Icon button | Background appears (transparent → 8% surface) |
| Input | Border color one step darker |
| Row in table/list | Background appears (transparent → 4% surface) |
Never make hover the only signal of interactivity. Touch users have no hover. Cursor and color shift together.
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 · 245 lines · 66 tokens per session scan A 11458ef8b590
canon-interaction is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 2,399 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-interaction compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-interactionDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 66 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| color-contrast-auditorcuriositech/windags-skills | Skill | 18 | 6d ago | none | A | 117 | Claude Code |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| lagannOldiiik/Design-Lagann | Skill | 2 | 18d ago | none | A | 0 | Claude Code, Codex |
| scroll-craftnateherkai/scroll-craft | Skill | 4.7k | 1mo ago | MIT | A | 177 | Claude Code |
| image-to-codeplugin87/ux-ui-agent-skills | Skill | 3.1k | 10d ago | MIT | A | 77 | Claude Code |