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 parisgroup-ai/imersao-ia-setup --skill i18n-maintenancegit clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setupWrote 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/parisgroup-ai/imersao-ia-setup/i18n-maintenance)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/i18n-maintenance"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/i18n-maintenance/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/parisgroup-ai/imersao-ia-setup/i18n-maintenance"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/i18n-maintenance.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 | $0.00067 | $0.03690 |
| Opus 5 | $0.00034 | $0.01845 |
| Sonnet 5 | $0.00013 | $0.00738 |
| Haiku 4.5 | $0.00007 | $0.00369 |
Grade A, and why
i18n-maintenance 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 12d 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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i18n Maintenance
Overview
Mantém consistência entre arquivos de tradução (i18n) em projetos multi-idioma. Valida estrutura, detecta chaves faltando, encontra traduções não utilizadas, valida sincronização código↔JSON e garante cobertura completa.
Princípio central: O locale en-US é a fonte de verdade para estrutura de chaves. Todos os outros locales devem ter a mesma estrutura.
Diferença desta Skill vs i18n-audit
| Skill | Foco | O que detecta |
|---|---|---|
| i18n-maintenance (esta) | Arquivos JSON + código | Chaves faltando, órfãs, estrutura, código↔JSON mismatch |
| i18n-audit | Código fonte (TSX/TS) | Textos hardcoded que deveriam usar t() |
Use esta skill quando: Validando arquivos de tradução ou erros de chave faltando Use i18n-audit quando: Procurando texto português hardcoded no código
When to Use
Use quando:
- Adicionar novas strings de tradução
- Verificar se todas as chaves estão traduzidas
- Encontrar traduções órfãs (não utilizadas no código)
- Erro
MISSING_MESSAGE: Could not resolve 'key'(código↔JSON mismatch) - Antes de deploy para garantir cobertura completa
- Após criar novas páginas/componentes com texto
Não use quando:
- Apenas lendo conteúdo traduzido
- Trabalhando em código sem strings i18n
- Procurando texto hardcoded (use
i18n-audit)
Estrutura do Projeto
apps/web/src/i18n/
├── config.ts # Configuração de locales
├── request.ts # Função getRequestConfig
└── messages/
├── en-US.json # ⭐ FONTE DE VERDADE + DEFAULT LOCALE
├── pt-BR.json
├── es-ES.json
├── fr-FR.json
└── de-DE.json
Locales suportados: en-US (default + fonte de verdade), pt-BR, es-ES, fr-FR, de-DE
Checklist de Validação
Execute na ordem:
1. Verificar Estrutura de Chaves (JSON ↔ JSON)
1.1 Extrair todas as chaves do locale de referência:
# Extrair chaves do en-US (fonte de verdade)
jq -r 'paths(scalars) | join(".")' apps/web/src/i18n/messages/en-US.json | sort > /tmp/keys-en-US.txt
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.
- 12d ago First seen · 440 lines · 67 tokens per session scan A 29a914826772
i18n-maintenance is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 3,690 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
tongwen
Use when translating engineering CAD drawings between languages — DWG text extraction, translation workspace with terminology management, quality-checked write-back. TongWen (同文): local-first CAD/BIM lossless translation suite for AutoCAD 2019-2026.
surface-after-care
Regelmäßiger Pflegedurchlauf für ein bereits veröffentlichtes GitHub-Repository (Stufe 1, günstig und oft wiederholbar): zuerst alle Distributionsflächen des Projekts ermitteln (npm, PyPI, Registries, Marketplaces, Stores, Website) und Änderungen später dorthin spiegeln, dann Topics setzen, Privacy-Gate, Dokumente auf…
full-after-care
Tiefe Pflegerunde für ein veröffentlichtes GitHub-Repository (Stufe 2): enthält den vollständigen surface-after-care-Durchlauf und ergänzt ihn um drei teure Schritte — rechtliche Ersteinschätzung über die Law-Checker mit Wiedervorlage nach einem Jahr (Gutachten bleibt gitignored im Repo), Querverweise zu verwandten…
bilingual-doc-sync
Parallel geführte Sprachfassungen eines Dokuments (Paper DE/EN, README + READMEde, SKILL.md + SKILL.en.md, Website-Texte) synchron halten: fehlende Fassung nachziehen, Abschnitts-Parallelität prüfen, Divergenzen beheben — mit klarer Leitsprache-Regel und kontrolliertem Rücktransfer, wenn die Nebenfassung etwas besser…
internationalization
Complete guide to internationalizing a Cumulocity Web SDK application. Covers all approaches to annotating and translating text (gettext, translate pipe, translate directive, TranslateService), extracting strings, creating and updating .po files, overriding existing translations, and adding brand-new languages.…
i18n Unused Key Review
Detect i18n/locale keys that are removed from source but remain in locale files, or keys added to locale files without source usage.