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 s0vers/next-app-i18n-starter --skill next-intl-i18ngit clone --depth 1 https://github.com/s0vers/next-app-i18n-starterWrote 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/s0vers/next-app-i18n-starter/next-intl-i18n)<a href="https://agentmods.dev/skills/s0vers/next-app-i18n-starter/next-intl-i18n"><img src="https://agentmods.dev/badge/skills/s0vers/next-app-i18n-starter/next-intl-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/s0vers/next-app-i18n-starter/next-intl-i18n"><img src="https://agentmods.dev/badge/skills/s0vers/next-app-i18n-starter/next-intl-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 | $0.00123 | $0.01756 |
| Opus 5.5 | $0.00049 | $0.00702 |
| Sonnet 5.5 | $0.00025 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
next-intl-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 16d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
next-intl in a Next.js App Router project
Five things must agree for every locale: the URL, the rendered language (lang and dir), the messages, the navigation, and the formatting. Every i18n bug is one of the five disagreeing with another. Find which pair disagrees before editing.
Both libraries move fast, and each reference dates its sources. Read the installed version in package.json before applying an example.
Recon
Always read package.json (next and next-intl versions) and the nearest AGENTS.md. Then read by task.
| Task | Also read |
|---|---|
| A message or a formatted value | dictionary/en.json and one other locale for the namespace, src/i18n/request.ts, src/i18n/regional.ts, global.d.ts |
| A redirect, prefix, cookie, or switcher problem | src/i18n/routing.ts, src/proxy.ts, next.config.ts, and host redirect rules (vercel.json, CDN) |
| Rendering, static output, or a new page | request.ts, [locale]/layout.tsx, the affected page |
| A new locale | src/i18n/locales.ts, every file in dictionary/, the layout, LanguageSwitcher.tsx, HomeIndex.tsx |
Recon is done when you can answer, one line each: which API path (below), which locale source, which rendering mode (static, dynamic, cached). A message-only task answers the last two with "unchanged".
If the config already does what the user asks, the fault is the deployment or a stale cache, not the source. Check the deployed response before editing.
| API path | Signals | Locale reaches server code through |
|---|---|---|
| Root params | Next >= 16.3 and [locale] hosts <html> |
next/root-params, automatic inside getTranslations |
| Legacy | requestLocale in request.ts, setRequestLocale in pages |
Explicit setRequestLocale(locale) before any next-intl call |
requestLocale and setRequestLocale are deprecated since next-intl 4.13.6 and 4.13.5. They still work. On an installed version older than 4.13.5 the deprecation does not apply yet, and the legacy path is simply current. Migrate one only when the task says so, and follow the migration steps in architecture.
What ships with it
10 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.
- evals/evals.json 5.8 KB
- references/architecture-and-rendering.md 6.6 KB
- references/integrations-and-workflows.md 4.6 KB
- references/localized-content.md 5.4 KB
- references/messages-and-formatting.md 6.7 KB
- references/routing-and-navigation.md 7.0 KB
- references/rtl-and-scripts.md 6.3 KB
- references/verification.md 4.7 KB
- scripts/check-locales.mjs 5.5 KB runs code
- scripts/check-messages.mjs 5.9 KB runs code
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.
- 16d ago First seen · 75 lines · 123 tokens per session scan A a3b7163c1d63
next-intl-i18n is a skill published in the GitHub repository s0vers/next-app-i18n-starter (66 stars, last pushed 6d ago), licensed MIT. It adds 123 tokens to every session and 1,756 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
tanstack-form
Headless, performant, and type-safe form state management for TS/JS, React, Vue, Angular, Solid, Lit, and Svelte.
ultracite
Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or reviewing JS/TS code in a project that uses Ultracite — to…
next-upgrade
Upgrade Next.js to the latest version following official migration guides and codemods.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
vercel-react-view-transitions
Guide for implementing smooth, native-feeling animations using React's View Transition API ( component, addTransitionType, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components…