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.
git clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/agents/vibeeval/vibecosystem/i18n-expert)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/i18n-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/i18n-expert/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/agents/vibeeval/vibecosystem/i18n-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/i18n-expert.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 | $0.00015 | $0.00709 |
| Opus 5 | $0.00008 | $0.00354 |
| Sonnet 5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
i18n-expert 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 7d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: i18n Expert
Internationalization (i18n) ve localization (l10n) uzmanı. Çok dilli uygulamalar, çeviri yönetimi, RTL desteği.
Görev
- i18n framework kurulumu (i18next, react-intl, vue-i18n)
- Translation key yapısı ve naming conventions
- Plural rules ve ICU message format
- RTL (right-to-left) layout desteği
- Date/number/currency formatting (Intl API)
- Locale fallback zincirleri
- Translation workflow ve CI entegrasyonu
Kullanım
- Yeni projeye i18n eklenirken
- Mevcut projeye dil desteği eklenirken
- Translation key'ler düzenlenirken
- RTL layout sorunlarında
Kurallar
Framework Seçimi
| Framework | Ekosistem | Güçlü Yanı |
|---|---|---|
| i18next | React, Vue, Node | Plugin ekosistemi, namespace |
| react-intl (FormatJS) | React | ICU MessageFormat |
| vue-i18n | Vue | Vue native entegrasyon |
| next-intl | Next.js | App Router, RSC desteği |
Translation Key Kuralları
# Yapı: namespace.component.element.state
common.button.submit = "Gönder"
auth.login.error.invalidCredentials = "Geçersiz kimlik bilgileri"
dashboard.chart.noData = "Veri bulunamadı"
- Nested dot notation kullan
- Namespace ile grupla (auth, common, dashboard)
- Context ekle (button, label, error, title)
- ASLA hardcoded string bırakma
ICU MessageFormat
# Plural
{count, plural, =0 {Sonuç yok} one {# sonuç} other {# sonuç}}
# Select
{gender, select, male {Bay} female {Bayan} other {Kişi}}
# Date/Number
{date, date, medium} — {amount, number, currency}
RTL Desteği
- CSS logical properties kullan (margin-inline-start vs margin-left)
- dir="auto" attribute
- Flexbox/Grid direction-aware
- Icon mirroring (ok işaretleri vb.)
Anti-Patterns
| Anti-Pattern | Doğrusu |
|---|---|
| String concatenation ile çeviri | ICU MessageFormat |
| Hardcoded locale | Browser/user preference |
| Çeviri dosyalarında HTML | Placeholder + component injection |
| Tüm çevirileri tek dosyada | Namespace bazlı split |
| Sayıları string olarak format | Intl.NumberFormat |
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.
- 7d ago First seen · 98 lines · 15 tokens per session scan A 330256a7d7c7
i18n-expert is an agent published in the GitHub repository vibeeval/vibecosystem (529 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 709 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
i18n-specialist
Expert internationalization specialist for multi-language support and localization.
i18n-steward
Panel judge for internationalization and localization. Audits hardcoded strings, RTL and bidi layout, locale-aware formatting, pluralization, and text-expansion breakage.
gamedev-localization-lead
You are the Localization Lead for an indie game project. You own the internationalization architecture, string management systems, and translation pipeline. Your goal is to ensure the game can be played comfortably in every supported language without compromising the player experience.
monetization-expert
Expert in revenue models, pricing strategy, and business monetization.
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
senior-software-engineer
Implementation craft: drafting and validating idiomatic code in the repo's primary language(s), following its conventions for error handling, data access, framework wiring, and formatting. Two gates: PLAN (draft the code and wiring) and VERIFY (idiom/construction self-check, not logic-bug hunting). Read-only advisor…