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-accordiongit 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-accordion)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-accordion"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-accordion/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-accordion"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-accordion.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 | $0.00089 | $0.02150 |
| Opus 5.5 | $0.00036 | $0.00860 |
| Sonnet 5.5 | $0.00018 | $0.00430 |
| Haiku 4.5 | $0.00009 | $0.00215 |
Grade A, and why
canon-accordion 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Accordions
An accordion is a disclosure widget — a heading that toggles content visibility. Useful in moderation. Often overused to hide things that should just be visible.
When to use an accordion
| Appropriate | Not appropriate |
|---|---|
| FAQ sections | Primary content users need to see |
| Optional settings users don't always expand | Forms (users miss fields they didn't open) |
| Long reference content organized into topics | Short content that fits on the page |
| Dense lists where each row has rich drill-down detail | Hiding critical errors or confirmations |
Don't use accordions to hide information users actually need. If the content matters, show it.
Use <details> / <summary> when possible
Native HTML gives you keyboard, screen reader, toggle state, and animation primitives for free.
<details>
<summary>What's your return policy?</summary>
<p>Returns accepted within 30 days of purchase. Items must be unused.</p>
</details>
- Enter / Space on
<summary>toggles. - Keyboard focus works natively.
- Screen readers announce expanded/collapsed.
- Default disclosure triangle can be styled or replaced.
- Use CSS
details[open]to animate.
Reach for custom ARIA only when native doesn't fit — e.g., controlling multiple sections with complex behavior.
Custom ARIA pattern
When <details> won't do:
<h3>
<button
aria-expanded="false"
aria-controls="panel-1"
id="trigger-1"
>
What's your return policy?
<svg aria-hidden="true">▼</svg>
</button>
</h3>
<div
id="panel-1"
role="region"
aria-labelledby="trigger-1"
hidden
>
<p>Returns accepted within 30 days.</p>
</div>
- Button wraps the heading text (not the heading itself).
- Heading element (
<h3>etc.) wraps the button to preserve document outline. aria-expandedtoggles true/false.aria-controlspoints to panel id.- Panel has
role="region"andaria-labelledby. - Hide with
hiddenattribute (ordisplay: none), notvisibility: hidden.
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 · 273 lines · 89 tokens per session scan A 105bd6d2539e
canon-accordion is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 89 tokens to every session and 2,150 once invoked, about $0.0004 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-accordion compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-accordionDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 89 | 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 |