intlayer: Skill for Claude Code

.agents/skills/intlayer-svelte/SKILL.md

intlayer-svelte is a skill for Claude Code, Codex from aymericzip/intlayer. It costs 53 tokens per session (863 once invoked), scanned A, original, Apache-2.0.

A translation setup for Svelte and SvelteKit applications using Intlayer, a system for managing text in multiple languages. Translations are declared near the components that use them.

In plain words
What is it for?
Use it to configure Intlayer, create translated Svelte components, and read their content with the `useIntlayer` store.
Why use it?
It keeps translated content organised by component instead of placing every translation in one large file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is aymericzip/intlayer's own configuration. It tells Claude Code and Codex how to work on intlayer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything intlayer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aymericzip/intlayer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aymericzip/intlayer/main/.agents/skills/intlayer-svelte/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aymericzip/intlayer

Made for: Claude Code, Codex.

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 intlayer-svelte

README.md
[![agentmods](https://agentmods.dev/badge/skills/aymericzip/intlayer/intlayer-svelte/github.svg)](https://agentmods.dev/skills/aymericzip/intlayer/intlayer-svelte)
Your own site
<a href="https://agentmods.dev/skills/aymericzip/intlayer/intlayer-svelte"><img src="https://agentmods.dev/badge/skills/aymericzip/intlayer/intlayer-svelte/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.

agentmods 80×15 button for intlayer-svelte

Your own site · 80×15
<a href="https://agentmods.dev/skills/aymericzip/intlayer/intlayer-svelte"><img src="https://agentmods.dev/badge/skills/aymericzip/intlayer/intlayer-svelte.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 863 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.00863
Opus 5.5 $0.00021 $0.00345
Sonnet 5.5 $0.00011 $0.00173
Haiku 4.5 $0.00005 $0.00086

Measured 14d ago against content hash 1fadedea96b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

intlayer-svelte 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 14d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/intlayer-svelte/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intlayer Svelte Usage

Core Philosophy

Intlayer promotes Component-Level Content Declaration. Instead of a massive global translation file, content is declared in *.content.ts files adjacent to the Svelte components that use them.

Workflow

To create a translated component, you need two files:

  1. Declaration: A content file (e.g., myComponent.content.ts) defining the dictionary.
  2. Implementation: A Svelte component (e.g., MyComponent.svelte) using the useIntlayer store.

1. Declare Content

Create a content file using t() for translations. File: src/components/MyComponent/myComponent.content.ts

import { t, type Dictionary } from "intlayer";

const content = {
  // The 'key' must be unique and matches what you pass to useIntlayer()
  key: "my-component",
  content: {
    text: t({
      en: "Welcome",
      fr: "Bienvenue",
      es: "Hola",
    }),
  },
} satisfies Dictionary;

export default content;

Setup

useIntlayer Hook

In Svelte, useIntlayer returns a store. You must use the $ prefix to access its value.

<script>
  import { useIntlayer } from "svelte-intlayer";
  const content = useIntlayer("my-component");
</script>

<div>
  <h1>
    {/* Return content */}
    {$content.text}
  </h1>
  {/* Return string (.value) */}
  <div aria-label={$content.text.value}></div>
</div>

Bundle Optimization

Read content fields by name (dot access or destructuring) so the build can purge and minify the dictionary. Never index content at runtime (content.statuses[status], use select()), and call useIntlayer in each child component instead of passing content as a prop. See the intlayer-bundle-optimization skill.

Compiler

The Intlayer Compiler can extract all your content keys from your components, using one CLI command (npx intlayer extract) or automatically at app build.

Read the full file on GitHub · 110 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. 14d ago Changed · +25 lines 1fadedea96b9
  2. 1mo ago First seen · 85 lines · 53 tokens per session scan A 8eab5e9ef165

Subscribe to this mod's changes

intlayer-svelte is a skill published in the GitHub repository aymericzip/intlayer (856 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 863 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

webiny-v5-to-v6-migration

Migration patterns for converting v5 Webiny code to v6 architecture. Use this skill when migrating existing v5 plugins to v6 features, converting context plugins to DI services, adapting v5 event subscriptions to v6 EventHandlers, or understanding how v5 patterns translate to v6. Targeted at AI agents performing…

webiny/webiny-js · 75 tokens

next-intl-i18n

Implement, migrate, or debug next-intl in a Next.js App Router project. Use when a change touches a locale URL, proxy, request config, message file, ICU message, formatted number, date, or list, RTL or CJK layout, localized CMS content, a locale switcher, or a translated error page. For canonicals, hreflang, sitemaps…

s0vers/next-app-i18n-starter · 123 tokens

nextjs-seo-international

Multilingual SEO for a Next.js site. Use for hreflang, es versus es-MX, one URL per language, partly translated content, translated titles and descriptions, machine translation quality, the locale switcher as a crawl path, and market launches. For a locale that is not indexed at all start with nextjs-seo-technical…

s0vers/next-app-i18n-starter · 91 tokens

localize-page

Convert or refactor Solana.com monorepo pages and their directly owned components to the repository's shared i18n system. Use when asked to internationalize, localize, remove hard-coded user-facing copy from, add translations to, or audit a page or route in apps/web, apps/docs, apps/media, apps/templates…

solana-foundation/solana-com · 103 tokens

use-ai-i18n-mcp

Use the eight local ai-i18n MCP tools to inspect missing or orphaned translations, update the configured JSON or SQLite Translation Memory, and manage reviewed overrides.json values. Use when working with aii18nlisttranslations, aii18nsettranslations, aii18ncleartranslations, aii18nlistorphanmessages…

bosens-China/tc39-atlas · 132 tokens

integrate-ai-i18n

Integrate ai-i18n into Vite browser projects that use Vue 3, React 18+, or vanilla JavaScript and TypeScript. Use when installing or configuring @ai-i18n/vite, adding translation calls or virtual:ai-i18n imports, selecting framework mode, enabling auto imports or ESLint, configuring optional locale loading or LLM…

bosens-China/tc39-atlas · 92 tokens