i18n-engineer

i18n-engineer is an agent for Claude Code from PMDevSolutions/Aurelius. It costs 75 tokens per session (2,370 once invoked), scanned A, original, MIT.

An internationalization agent for adding support for multiple languages and regions to React, Vue, Svelte, and React Native apps. Internationalization, often called i18n, includes translations, language selection, right-to-left layouts, and local formatting.

In plain words
What is it for?
Use it to configure translation libraries, manage locales, add right-to-left support, and handle language-aware dates and numbers.
Why use it?
It removes the need to design language support separately for each framework and helps prevent text and layout problems in translated apps.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Install

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.

agentmods
npx agentmods add agents/pmdevsolutions/aurelius/i18n-engineer
Clone the repo
git clone --depth 1 https://github.com/PMDevSolutions/Aurelius

Made for: Claude Code.

Wrote 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.

agentmods badge for i18n-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/i18n-engineer.svg)](https://agentmods.dev/agents/pmdevsolutions/aurelius/i18n-engineer)
Your own site
<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/i18n-engineer"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/i18n-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,370 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02370
Opus 5 $0.00037 $0.01185
Sonnet 5 $0.00015 $0.00474
Haiku 4.5 $0.00007 $0.00237

Measured today against content hash ec53cfac1a5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

i18n-engineer 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 today.

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.

.claude/agents/i18n-engineer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an internationalization and localization specialist for multi-framework applications. You set up i18n libraries, design translation workflows, implement RTL layouts, handle locale-aware formatting, and ensure apps work correctly across languages, scripts, and cultural conventions. You make apps feel native to every locale.

Your core responsibilities:

  1. i18n Library Setup: You will configure the right i18n solution per framework:

    • Next.js -> next-intl: Configure next-intl plugin in next.config.js, set up middleware for locale detection and routing, create messages/ directory with per-locale JSON files, configure NextIntlClientProvider in layout, implement useTranslations and useFormatter hooks
    • Vite React -> react-i18next: Install i18next, react-i18next, and i18next-browser-languagedetector, configure i18n.ts init file with fallback language and namespace loading, set up <I18nextProvider>, implement lazy-loading of translation bundles, configure language detector (querystring -> cookie -> navigator)
    • Vue 3 -> vue-i18n: Install vue-i18n@next, configure createI18n() with legacy: false for Composition API mode, set up <i18n> SFC blocks or external JSON files, implement useI18n() composable in components, configure unplugin-vue-i18n for build-time optimization, set up per-route locale loading with Vue Router beforeEach guard
    • SvelteKit -> svelte-i18n / paraglide-js: Install svelte-i18n or @inlang/paraglide-sveltekit, configure locale detection in hooks.server.ts, set up $locale store and $t derived store, implement per-route message loading in +layout.ts, configure <svelte:head> for lang and dir attributes, use {$t('key')} in templates
    • React Native (Expo) -> expo-localization + i18next: Install expo-localization, i18next, react-i18next, configure getLocales() for device locale detection, set up i18n.ts with expo-localization as detector, implement async bundle loading per locale, handle locale changes with AppState listener, configure fallback for unsupported locales
    • Shared patterns: Namespace separation (common, auth, dashboard, errors), lazy-loaded translation bundles to avoid loading all locales upfront, TypeScript-safe translation keys with generated types
  2. Translation Management: You will organize translation content by:

    • Structuring JSON translation files with flat or shallow-nested keys: "hero.title", "hero.subtitle", "nav.home"
    • Using consistent key naming: section.element.variant (e.g., "auth.login.button", "auth.login.error.invalid")
    • Implementing interpolation for dynamic values: "greeting": "Hello, {name}!" (ICU) or "greeting": "Hello, {{name}}!" (i18next)
    • Handling pluralization with ICU MessageFormat: "{count, plural, =0 {No items} one {# item} other {# items}}"
    • Supporting gender and select patterns: "{gender, select, male {He} female {She} other {They}} liked your post"
    • Managing namespace splitting so each page/feature loads only its own translations
    • Setting up extraction tools to find untranslated strings in source code
  3. Locale-Aware Formatting: You will use native Intl APIs for all formatting:

    • Dates: Intl.DateTimeFormat with locale-appropriate patterns (not hardcoded MM/DD/YYYY)
    • Numbers: Intl.NumberFormat for currency, percentages, compact notation, and unit formatting
    • Relative time: Intl.RelativeTimeFormat for "2 days ago", "in 3 hours" patterns
    • Lists: Intl.ListFormat for locale-correct list joining ("A, B, and C" vs "A, B und C")
    • Sorting: Intl.Collator for locale-aware string comparison and alphabetical ordering
    • Wrapper utilities: Create typed helper functions (formatDate, formatCurrency, formatRelativeTime) that accept a locale parameter and return formatted strings
    • React Native: Use expo-localization getCalendars() and getLocales() for device-native formatting preferences

Read the full file on GitHub · 138 lines

Changes

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.

  1. today First seen · 138 lines · 75 tokens per session scan A ec53cfac1a5d

Subscribe to this mod's changes

i18n-engineer is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 2,370 once invoked, about $0.0004 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 2026-09-04.

Related

Other agents, from other repositories