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-i18ngit 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-i18n)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-i18n"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-i18n/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-i18n"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-i18n.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 | $0.00060 | $0.01159 |
| Opus 5 | $0.00030 | $0.00580 |
| Sonnet 5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
canon-i18n 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 10d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Internationalization
I18n is preparing the codebase so that adding a new language doesn't require rewriting the UI. L10n is the act of adding one.
Externalize all strings
No user-visible string lives in source code. Every string goes through a translation function.
// Bad
<button>Save changes</button>
// Good
<button>{t('actions.save_changes')}</button>
Keys are structured, not sequential: actions.save_changes not string_47.
Text expansion
German is 30–40% longer than English. Finnish, Russian, and Arabic can be longer still. Japanese and Chinese are often shorter.
| Language | Expansion vs English |
|---|---|
| German | +30–40% |
| French | +15–25% |
| Russian | +20–30% |
| Japanese | -20–30% |
| Arabic | +20–30% |
Design for 40% expansion. If a label barely fits in English, it breaks in German.
Test with pseudo-localization: replace strings with accented, expanded versions ([Ŝàvé çhàñgéŝ!!!!]) to catch overflow before real translations arrive.
Never concatenate strings
// Bad — word order varies by language
`Welcome, ${name}. You have ${count} messages.`
// Good — use ICU message format
t('welcome', { name, count })
// en: "Welcome, {name}. You have {count, plural, one {# message} other {# messages}}."
// ja: "{name}さん、{count}件のメッセージがあります。"
Concatenation assumes English word order. Interpolation with named variables lets translators reorder.
Pluralization — ICU MessageFormat
English has 2 plural forms (singular, plural). Arabic has 6. Polish has 4. Use ICU {count, plural, ...} for every countable string.
{count, plural,
=0 {No messages}
one {# message}
other {# messages}
}
Libraries: intl-messageformat, i18next with ICU plugin, FormatJS.
Date, time, number formatting
Use Intl APIs. Never manually format.
new Intl.DateTimeFormat('de-DE', { dateStyle: 'long' }).format(date);
// "18. April 2026"
new Intl.NumberFormat('en-IN').format(1234567);
// "12,34,567"
- Dates:
Intl.DateTimeFormat. Month/day order varies by locale. - Numbers:
Intl.NumberFormat. Thousands/decimal separators vary. - Currency:
Intl.NumberFormatwithstyle: 'currency'. Symbol position varies. - Relative time:
Intl.RelativeTimeFormat. "3 days ago" / "vor 3 Tagen".
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.
- 10d ago First seen · 132 lines · 60 tokens per session scan A 2f3763c767c1
canon-i18n is a skill published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,159 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
ttb-skill-audit
Code audits for TTBaseUIKit apps: performance, accessibility, localization. FCR compliance scoring.
ios-localization
Implement, review, or improve localization and internationalization in iOS/macOS apps — String Catalogs (.xcstrings), generated localizable symbols, stable key naming, LocalizedStringKey, LocalizedStringResource, pluralization, FormatStyle for numbers/dates/measurements, right-to-left layout, Dynamic Type, and…
natural-language
Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translation framework. Use when adding language identification, sentiment analysis, named entity recognition, part-of-speech tagging, text embeddings, or in-app translation to…
swift-formatstyle
Formats and parses locale-aware numbers, decimals, currencies, percentages, dates, durations, measurements, names, lists, byte counts, and URLs with Foundation FormatStyle and ParseableFormatStyle. Use when replacing legacy Formatter subclasses, designing reusable format APIs, using SwiftUI Text(:format:), correcting…
accessibility
Accessibility (a11y) workflow skill. Use this skill when the user needs Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". Do NOT use for SEO (use seo)…
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.