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-searchgit 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-search)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-search"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-search/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-search"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-search.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 | $0.00088 | $0.02259 |
| Opus 5.5 | $0.00035 | $0.00904 |
| Sonnet 5.5 | $0.00018 | $0.00452 |
| Haiku 4.5 | $0.00009 | $0.00226 |
Grade A, and why
canon-search 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Search
Search is where users land when the nav fails them. Make it fast, forgiving, and keyboard-first.
The search input itself
<form role="search">
<label for="q" class="sr-only">Search</label>
<svg aria-hidden="true" class="search-icon">...</svg>
<input
id="q"
type="search"
name="q"
placeholder="Search projects, files, people…"
autocomplete="off"
spellcheck="false"
autocapitalize="off"
autocorrect="off"
/>
<button type="button" aria-label="Clear search" class="clear-btn" hidden>✕</button>
</form>
<form role="search">wraps the input — gives screen reader context.<label>is always present (can be visually hidden).type="search"— mobile keyboard shows a "search" button, browsers add a clear-X.- Turn off
autocomplete,spellcheck,autocapitalize,autocorrectfor identifier-like searches; leave on for natural-language search. - Custom clear button for consistent look (native X is inconsistent across browsers).
Input visual spec
| Property | Value |
|---|---|
| Height | 36–48px (40px default) |
| Horizontal padding | 36–40px left (room for icon), 32–40px right (room for clear) |
| Font size | 14–16px (16px on mobile — iOS zooms inputs < 16px) |
| Icon size | 16–18px, currentColor, muted |
| Border radius | 6–8px for fields, fully rounded (999px) for pill style |
| Focus ring | 2–3px offset 2px, 3:1 contrast minimum |
Placeholder — show examples, not instructions
| Bad | Good |
|---|---|
| Search | Search projects, files, people |
| Enter keywords | Try "Q4 roadmap" |
| Type to search | Find teammates, tickets, docs |
Placeholder is a preview of what you can do. It disappears on focus, so it can't be the label.
Debouncing
| Action | Delay |
|---|---|
| Keystroke → fetch suggestions | 150–250ms debounce |
| Keystroke → render suggestions (client-side) | 0ms |
| Keystroke → run full search (submit) | Only on Enter or search button |
150–250ms is the sweet spot: fast enough to feel responsive, slow enough to avoid firing a request per keypress.
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 · 255 lines · 88 tokens per session scan A c2adc6a59f3e
canon-search is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 2,259 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 2026-09-03.
canon-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-searchDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 88 | 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 |