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-imagesgit 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-images)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-images"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-images/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-images"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-images.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 | $0.00075 | $0.00967 |
| Opus 5.5 | $0.00030 | $0.00387 |
| Sonnet 5.5 | $0.00015 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
canon-images 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Images
Images are the largest payload on most pages. Format, size, and loading strategy make or break performance.
Format decision tree
Is it a photo or complex gradient?
├─ Yes → AVIF (best compression), WebP fallback, JPEG last resort
└─ No →
Is it an icon, logo, or simple shape?
├─ Yes → SVG (infinitely scalable, tiny file)
└─ No →
Does it need transparency?
├─ Yes → WebP or PNG (WebP preferred, smaller)
└─ No → AVIF/WebP/JPEG
Responsive images — srcset
Serve the right size for the viewport. Don't send a 2400px image to a 375px phone.
<img
src="hero-800.webp"
srcset="hero-400.webp 400w, hero-800.webp 800w, hero-1200.webp 1200w, hero-1600.webp 1600w"
sizes="(max-width: 768px) 100vw, 50vw"
alt="Product showcase"
width="1200"
height="800"
loading="lazy"
decoding="async"
>
LCP image — the critical one
The Largest Contentful Paint image needs special treatment:
- No
loading="lazy"— it must load eagerly. fetchpriority="high"— tells the browser to prioritize.- Preload —
<link rel="preload" as="image" href="hero.webp">. - Serve at rendered size — don't serve 3000px for a 600px container.
<link rel="preload" as="image" href="hero.webp" fetchpriority="high">
<img src="hero.webp" alt="..." width="1200" height="800" fetchpriority="high">
Always declare width and height
<img src="photo.webp" alt="..." width="800" height="600">
This reserves layout space before the image loads, preventing Cumulative Layout Shift (CLS). The browser calculates aspect ratio from these attributes. CSS can still make the image responsive:
img { max-width: 100%; height: auto; }
Lazy loading
All images below the fold should use loading="lazy". Native browser lazy loading works without JavaScript.
Exception: the LCP image (above the fold) must NOT be lazy loaded.
Image CDNs
Services like Cloudinary, imgix, Cloudflare Images serve optimized formats and sizes automatically:
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 · 111 lines · 75 tokens per session scan A 91eb1872ebd2
canon-images is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 75 tokens to every session and 967 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-images compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-imagesDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 75 | 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 |
| Website AuditPramodDutta/qaskills | Skill | 245 | 4d ago | MIT | A | 33 | Claude Code, Codex |
| huawei-cloud-cts-trace-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 249 | Claude Code |
| accessibility-auditoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |
| a11y-auditgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 147 | Claude Code |