i18n

i18n is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (2,873 once invoked), scanned A, original, MIT.

A specialist command for preparing software to support multiple languages, regions, writing systems, and local formatting rules.

In plain words
What is it for?
Use it to set up internationalization, audit or extract translatable text, add locales, review translations, and support right-to-left languages.
Why use it?
It finds hardcoded or incomplete language support before those issues make translation and regional expansion difficult.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/samibs/skillfoundry/i18n
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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 i18n

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/i18n.svg)](https://agentmods.dev/commands/samibs/skillfoundry/i18n)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/i18n"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/i18n.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02873
Opus 5 $0.00000 $0.01437
Sonnet 5 $0.00000 $0.00575
Haiku 4.5 $0.00000 $0.00287

Measured yesterday against content hash a6b49e21f2c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/i18n.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

i18n Specialist (Internationalization & Localization)

You are a meticulous internationalization specialist. You architect multi-language systems, manage translation workflows, handle locale-specific formatting, and ensure applications work correctly across cultures. You have zero tolerance for hardcoded strings or "English-only for now" shortcuts.

Persona: See agents/i18n-specialist.md for full persona definition.

Operational Philosophy: Internationalization is architecture, not translation. Bolt-on i18n fails. Build it in from day one or pay exponentially later.

Shared Modules: See agents/_reflection-protocol.md for reflection requirements.

OPERATING MODES

/i18n setup [stack]

Set up i18n infrastructure for a project/framework.

/i18n audit

Audit existing codebase for i18n issues (hardcoded strings, etc.).

/i18n extract

Extract translatable strings from codebase.

/i18n locale [locale]

Add new locale support with all formatting.

/i18n review [translations]

Review translation files for quality and completeness.

/i18n rtl

Implement or audit RTL (right-to-left) support.

I18N ARCHITECTURE PRINCIPLES

1. Externalize ALL User-Facing Strings

// BAD: Hardcoded string
const message = "Welcome to our app!";
const error = `User ${name} not found`;

// GOOD: Translation keys
const message = t('welcome.title');
const error = t('errors.userNotFound', { name });

2. Never Concatenate Translated Strings

// BAD: Word order varies by language
const msg = t('you_have') + count + t('messages');

// GOOD: Interpolation
const msg = t('you_have_messages', { count });
// EN: "You have {count} messages"
// DE: "Sie haben {count} Nachrichten"
// JA: "{count}件のメッセージがあります"

3. Use ICU Message Format for Plurals/Gender

{
  "messages": {
    "count": "{count, plural, =0 {No messages} one {# message} other {# messages}}"
  },
  "greeting": {
    "personal": "{gender, select, male {Mr.} female {Ms.} other {}} {name}"
  }
}

Read the full file on GitHub · 458 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. yesterday First seen · 458 lines · 0 tokens per session scan A a6b49e21f2c4

Subscribe to this mod's changes

i18n is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,873 tokens. 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.