agentmods.dev

globalize-guide

globalize-guide is a skill for Claude Code, Codex from globalize-now/globalize-skills. It costs 268 tokens per session (35,961 once invoked), scanned D, original, MIT.

An internationalization workflow for adapting a software project to multiple languages and regions. It detects the technology stack, helps choose and configure a translation library, converts existing text, and can connect Globalize for translation management.

In plain words
What is it for?
Use it to add or configure multilingual support, wrap hardcoded interface text, build translation catalogs, and connect the project to Globalize.
Why use it?
It organizes the many steps needed to add localization instead of leaving translated text, catalogs, and repository setup disconnected. Globalize connection is included by default but can remain out of scope.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is 1. Run `npx '@inlang/paraglide-js@^2' compile --project ./project.inlang --outdir ./src/lib/paraglide` (both flags; single-quoted pin so zsh's `EXTENDED_GLOB` d.

not rated 3repo yesterday D scan 268 tokens original MIT

Good fit Use it to add or configure multilingual support, wrap hardcoded interface text, build translation catalogs, and connect the project to Globalize.

Compare 6 skills from other repositories ↓
View source ↗ globalize-now/globalize-skills
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/globalize-now/globalize-skills
agentmods
npx agentmods add skills/globalize-now/globalize-skills/globalize-guide

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 globalize-guide

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/globalize-now/globalize-skills/globalize-guide"><img src="https://agentmods.dev/badge/skills/globalize-now/globalize-skills/globalize-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 268 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 35,961 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00268 $0.35961
Opus 5 $0.00134 $0.17980
Sonnet 5 $0.00054 $0.07192
Haiku 4.5 $0.00027 $0.03596

Measured 9d ago against content hash 3a22e21b87af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

globalize-guide scanned grade D with 3 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 9d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- [ ] gitignore_artifacts <!-- libraries that emit on-disk generated catalogs only. Lingui: the compiled `.ts`/`.js` siblings of the committed `.po` sources. Paraglide: the compiler `outdir` (`src/lib/paraglide/`). Runs

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

If `existing.configured === true`, `plan.md` reduces Phase 2 to a verify-and-complete plan (verify what exists, add only what's missing — no from-scratch `create_config`): `verify_config`, `verify_provider`, `add_missing

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **User-selectable picker** — the extension reads its own catalogs and stores the choice in `browser.storage.sync`. Records `decisions.setup.localeSwitcher = "custom-loader"`. On the **Lingui** variant this is always th
skills/globalize-guide/SKILL.md · 986 lines

How it starts

The opening of the file, as written. The whole thing — 986 lines — stays where its author put it; the contents beside it link to each section on GitHub.

i18n Orchestrator

This skill drives the full i18n journey through five stages:

Stage Goal
1 — Inspect and decide Detect stack, ask all user questions, generate an executable plan
1.5 — Globalize account (upfront) Install CLI + sign in + verify org via globalize-now-account-setup
2 — Setup Install + configure the chosen library
3 — Convert Wrap hardcoded strings, extract + compile catalogs
4 — Globalize project (end) Create project + connect repo + set patterns via globalize-now-project-setup

Stages 1.5 and 4 only run when the user keeps Globalize connection in scope (default-on; see 1.6). The Globalize work is split deliberately: account creation is interactive and project-independent, so it runs upfront while the user is engaged; project + repo setup needs the converted catalog paths, so it runs at the end.

The orchestrator (this SKILL.md) is library-agnostic. Library- and stack-specific guidance lives in references/ and is loaded by subagents at dispatch time, driven by manifest.json.

Architectural rule: the orchestrator never executes work directly. It asks Phase 1 questions, generates the plan, dispatches subagents in the background, polls a shared progress workspace at .globalize/, and surfaces results. All file modifications, all bash commands, and all reference reading happen inside subagents. One carve-out: the interactive Globalize steps (account sign-in in 1.5, project + repo connection in Phase 4) run on the main thread by delegating to the globalize-now-account-setup / globalize-now-project-setup skills via the Skill tool — the orchestrator never inlines Globalize CLI commands itself (those skills own the authoritative command surface).

Workspace: .globalize/

Created in the target project root (the project being internationalized). Every artifact the orchestrator and subagents share lives here.

.globalize/
  detection.json              # output of inspect subagent (Phase 1.1)
  decisions.md                # frozen user choices from Phase 1
  plan.md                     # executable plan for phases 1.5/2/3/4
  manifest-snapshot.json      # frozen copy of the chosen manifest entry
  rules-values.json           # resolved template conditions and values; written by the core `generate_coding_rules` step in Phase 2, consumed when rendering `.agents/globalize-rules.md`
  globalize-inputs.json       # resolved Globalize project inputs (written in Phase 4, read by globalize-now-project-setup)
  progress/
    setup.json                # Phase 2 setup subagent
    wrap-1.json…wrap-N.json   # Phase 3 wrap subagents (one per partition)
    verify.json               # Phase 3 verify subagent
    archive/<ISO-timestamp>/  # archived after each phase completes

Read the full file on GitHub · 986 lines

Files

What ships with it

60 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.

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. 9d ago First seen · 986 lines · 268 tokens per session scan D 3a22e21b87af

Subscribe to this mod's changes

globalize-guide is a skill published in the GitHub repository globalize-now/globalize-skills (3 stars, last pushed yesterday), licensed MIT. It adds 268 tokens to every session and 35,961 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it D with 3 findings (hidden instructions, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeLocalizationagent-skillsclaude-skillscursori18n
Related

Other skills, from other repositories

extract-source-sample

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…

gooseworks-ai/goose-skills · 160 tokens

audit-i18n

Audit and fix internationalisation for any web or mobile app. Use when asked to "audit i18n", "fix translations", "add locale", "natural language", "translation quality", "hardcoded strings", "localisation", or "the Japanese feels like Google Translate".

kensaurus/cursor-kenji · 61 tokens

nextjs-locale-monorepo

Add locale-prefixed i18n routing across a Next.js monorepo (Turborepo / pnpm workspaces) by extracting the engine into a shared workspace package that every app consumes — locale detection + a middleware/proxy factory + a use client LocaleProvider/hooks, plus a shared supportedLanguages config. Each app redirects /…

stealth-factory/skills · 210 tokens

nextjs-locale-standalone

Add locale-prefixed i18n routing to a single (non-monorepo) Next.js App Router site — a middleware/proxy that redirects / and any unprefixed path to / /… using the locale toggle's last choice (the NEXTLOCALE cookie) then the browser's Accept-Language, a [locale] layout with a LocaleProvider + hooks, and a LocaleToggle…

stealth-factory/skills · 184 tokens

thai-resume

Use this skill for any task involving Thai-language or bilingual (TH/EN) resumes and CVs. Trigger whenever the user asks to: write a Thai resume, draft a CV in Thai, build a bilingual Thai-English resume, format an application for a Thai employer, choose between พ.ศ. and ค.ศ. dates in a CV, or tailor a resume for…

Boom-Vitt/claude-thai-skills · 146 tokens

thai-text-processing

Use this skill for any task involving Thai text in code — word segmentation, Unicode normalization, sorting/collation, search indexing, romanization, truncation, or database/Elasticsearch configuration for Thai. Trigger whenever the user asks to: tokenize / segment Thai (no spaces between words), normalize Thai text…

Boom-Vitt/claude-thai-skills · 193 tokens