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 agentmods add skills/fusengine/agents/nextjs-i18nnpx skills add fusengine/agents --skill nextjs-i18ngit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/nextjs-i18n)<a href="https://agentmods.dev/skills/fusengine/agents/nextjs-i18n"><img src="https://agentmods.dev/badge/skills/fusengine/agents/nextjs-i18n.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01529 |
| Opus 5 | $0.00017 | $0.00764 |
| Sonnet 5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
nextjs-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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Covers [locale]-prefixed routing, localized navigation components (Link, redirect, usePathname, useRouter), date/number/currency/relative-time formatting, RTL language support, SEO hreflang tags, and localized special files ([locale]/error.tsx, [locale]/not-found.tsx, global-error.tsx). This is the Next.js-specific i18n skill (App Router routing, proxy.ts integration) — for plain React apps without Next.js see react-i18n, and for Astro see astro-i18n.
Next.js 16 Internationalization
Complete i18n solution with next-intl or DIY dictionary approach.
Agent Workflow (MANDATORY)
Before ANY implementation, use TeamCreate to spawn 3 agents:
- fuse-ai-pilot:explore-codebase - Analyze existing i18n setup and message files
- fuse-ai-pilot:research-expert - Verify latest next-intl docs via Context7/Exa
- mcp__context7__query-docs - Check locale config and patterns
After implementation, run fuse-ai-pilot:sniper for validation.
Overview
When to Use
- Building multilingual Next.js 16 applications
- Need locale-based routing with
[locale]dynamic segment - Implementing language switcher and URL localization
- Formatting dates, numbers, currencies, and relative times per locale
- SEO optimization with hreflang tags and localized metadata
- Supporting right-to-left (RTL) languages
Why next-intl
| Feature | Benefit |
|---|---|
| App Router native | Full Server Components support |
| Type-safe messages | TypeScript autocompletion for keys |
| ICU MessageFormat | Pluralization, gender, select expressions |
| Async message loading | Load translations on-demand per locale |
| proxy.ts compatible | Works with Next.js 16 proxy pattern |
| Rich formatting | Dates, numbers, lists, relative time |
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/client-components.md 2.7 KB
- references/configuration.md 2.1 KB
- references/core-library.md 2.0 KB
- references/diy-dictionaries.md 2.5 KB
- references/diy-locale-detection.md 2.9 KB
- references/error-files.md 2.1 KB
- references/extraction.md 1.9 KB
- references/formatting.md 2.3 KB
- references/installation.md 2.3 KB
- references/integrations.md 2.0 KB
- references/messages-validation.md 2.4 KB
- references/middleware-proxy.md 2.5 KB
- references/navigation.md 2.6 KB
- references/pages-router.md 2.4 KB
- references/plugin.md 1.8 KB
- references/routing-config.md 2.5 KB
- references/routing-setup.md 2.6 KB
- references/runtime-requirements.md 2.0 KB
- references/seo.md 2.5 KB
- references/server-components.md 2.8 KB
- references/testing.md 2.6 KB
- references/translations.md 2.2 KB
- references/typescript.md 2.4 KB
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.
- yesterday First seen · 167 lines · 35 tokens per session scan A eee5eafd4568
nextjs-i18n is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,529 once invoked, about $0.0002 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 skills, from other repositories
create-kr-patch
Use for Korean (Hangul) fan translations of retro console or PC games, including ROM or disc analysis, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction and reinsertion, code hooks, reproducible product builds, and emulator verification. Apply it to new investigations and follow-up…
fec-drawio-studio
用于创建带 draw.io / diagrams.net 源文件的可编辑技术图，包括架构图、ERD、UML、序列图、流程图、ML 模型图、官方形状检索、品牌符号、Graphviz 自动布局、代码结构图、.drawio 校验或 draw.io CLI 导出兜底。不要用于普通位图生成、手绘草图、交互式 Canvas/Three.js 场景或装饰性 SVG 动画；中文触发词包括 draw.io、diagrams.net、可编辑架构图、.drawio、ER 图、UML、序列图、自动布局、形状检索、代码结构图。.
fec-component-testing
用于编写或审查靠近 UI 代码的前端单元、组件或轻量集成测试，包括 React Testing Library、Vue Test Utils、hooks/composables、props/emits、回调、可访问查询、user-event 交互、mock、loading/error/empty 状态和回归覆盖。若是测试分层规划、真实浏览器旅程或现有验证失败，优先选择对应测试或验证工作流；中文触发词包括 组件测试、组件单测、单元测试、轻量集成测试。.
fec-nuxt-project-standard
用于创建或审查 Nuxt 3 项目、文件路由、pages、layouts、SSR/SSG/SPA 行为、Nuxt 数据获取、route middleware、plugins、modules、server routes 或 Nuxt 特定 Vue 3 约定。通用 Vue 组件架构另按项目 Vue 约定处理；中文触发词包括 Nuxt、Nuxt 3。.
fec-route-protection
用于实现或审查前端路由保护、auth guard、RBAC、权限路由、登录态处理、重定向、middleware、React Router、Next.js、Vue Router 或 Nuxt route middleware；中文触发词包括 路由保护、权限路由、登录态。.
fec-state-management
用于选择、实现、审查或重构 React、Vue、Next.js、Nuxt、URL 状态、服务端状态、表单状态、浏览器持久化或全局 store 的前端状态归属。TanStack Query 缓存细节、浏览器存储持久化或表单校验内部问题优先使用更窄的 skill；中文触发词包括 状态管理、状态归属、store 选型。.