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-rtlgit 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-rtl)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-rtl"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-rtl/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-rtl"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-rtl.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 | $0.01057 |
| Opus 5.5 | $0.00030 | $0.00423 |
| Sonnet 5.5 | $0.00015 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
canon-rtl 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · RTL
RTL is not "flip everything." It's about reading direction. Text, layout flow, and directional icons mirror. Decorative elements, media controls, and universal icons do not.
Set the direction
<html lang="ar" dir="rtl">
dir="rtl" on <html> flips the entire document flow. Browser handles most text and flexbox/grid automatically.
Use CSS logical properties
Physical properties break in RTL. Logical properties work in both directions automatically.
| Physical (avoid) | Logical (use) |
|---|---|
margin-left |
margin-inline-start |
margin-right |
margin-inline-end |
padding-left |
padding-inline-start |
text-align: left |
text-align: start |
float: left |
float: inline-start |
left: 0 |
inset-inline-start: 0 |
border-left |
border-inline-start |
.sidebar { margin-inline-start: 24px; padding-inline-end: 16px; }
What mirrors (flips in RTL)
- Text alignment and flow
- Flex and grid direction (row → row-reverse)
- Navigation order (left-to-right becomes right-to-left)
- Breadcrumbs (Home > Products becomes Products < Home)
- Directional icons: back arrow, forward arrow, chevrons pointing "forward/backward"
- Progress bars, sliders, timeline direction
- Lists with indentation
- Form layout: labels relative to inputs
What does NOT mirror
- Media playback controls (play/pause/seek are universal)
- Phone number fields (always LTR, digits are universal)
- Clocks (clockwise is universal)
- Logos and brand marks
- Checkmarks, plus/minus, close X
- Up/down arrows (vertical is directionless)
- Images and photos (don't flip)
- Charts with mathematical axes (0 at origin)
- Slash direction in paths (/Users/path)
Bidirectional text (bidi)
Mixed LTR and RTL content in the same string (e.g., Arabic text with an English brand name):
<p>مرحباً بك في <bdi>CANON</bdi> للتصميم</p>
<bdi>isolates the embedded text direction.- Never rely on Unicode control characters manually. Use HTML elements.
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 · 119 lines · 75 tokens per session scan A 9d0cc562317b
canon-rtl 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 1,057 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-rtl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-rtlDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 75 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| rtl-internationalizationMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 72 | Claude Code |
| wp-header-runyojahny55/claude-wp-builder | Skill | 6 | 4d ago | MIT | A | 133 | Claude Code |
| accessibility-auditNickCrew/Claude-Cortex | Skill | 66 | 4mo ago | MIT | A | 31 | Claude Code, Codex |
| ttb-skill-audittqtuan1201/TTBaseUIKit | Skill | 23 | 3mo ago | MIT | A | 26 | Claude Code, Codex |
| ios-localizationdpearson2699/swift-ios-skills | Skill | 1.3k | 3mo ago | none | A | 127 | Claude Code |