localization

localization is a skill for Claude Code, Codex from furkangonel/cowrangler. It costs 25 tokens per session (740 once invoked), scanned A, original, MIT.

A writing guide for adapting text to a specific language and region so it sounds natural to local readers, not merely translated word for word.

In plain words
What is it for?
Adapt interface text, product messages, documentation, legal content, and marketing copy for a named audience and locale.
Why use it?
It helps avoid awkward wording, unsuitable cultural references, and the wrong level of formality in user-facing or promotional text.

Skill for Claude CodeCodex

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 skills/furkangonel/cowrangler/localization
Any agent
npx skills add furkangonel/cowrangler --skill localization
Clone the repo
git clone --depth 1 https://github.com/furkangonel/cowrangler

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 localization

README.md
[![agentmods](https://agentmods.dev/badge/skills/furkangonel/cowrangler/localization.svg)](https://agentmods.dev/skills/furkangonel/cowrangler/localization)
Your own site
<a href="https://agentmods.dev/skills/furkangonel/cowrangler/localization"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/localization.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 740 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 $0.00025 $0.00740
Opus 5 $0.00013 $0.00370
Sonnet 5 $0.00005 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 5d ago against content hash c56e1770f0c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

localization 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 5d 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.

bundled_skills/localization/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Localization Skill

Goal

Produce target-language content that feels like it was written natively — not translated. Preserve meaning and intent while adapting cultural references, idioms, tone, and register for the target audience.

Distinction: Translation vs. Localization vs. Transcreation

Mode When to use
Translation Technical docs, legal text, factual content — accuracy > naturalness
Localization UI strings, user-facing messages, product copy — natural + accurate
Transcreation Marketing slogans, emotional copy, humor — intent and feeling > literal meaning

Identify which mode applies before starting.

Steps

1. Identify source and target

Confirm: source language, target locale (e.g. tr-TR, de-DE, not just German), content type (UI, marketing, technical, legal).

If the target locale isn't specified, ask.

Success criteria: You know the exact target audience (region + formality level).

2. First pass — literal translation

Translate accurately, preserving all meaning. Note every idiom, cultural reference, or humor that won't land in the target culture — flag with [ADAPT].

Success criteria: Nothing is lost in meaning; adaptation candidates are clearly marked.

3. Second pass — cultural adaptation

For each [ADAPT] flag:

  • Replace idioms with target-culture equivalents (not literal translations)
  • Adjust formality: Turkish has T/V distinction (sen/siz); German has du/Sie — match the brand voice
  • Localize examples, measurements, date formats, currency
  • Adapt humor: if it doesn't translate, replace with something that achieves the same effect

Success criteria: A native speaker would not identify the text as translated.

4. Technical localization (if applicable)

  • Placeholder handling: {name}, %s, {{variable}} — preserve all placeholders exactly
  • String length: UI strings often have length constraints — flag anything that grew >20%
  • RTL languages: flag if target is Arabic/Hebrew and layout changes may be needed

Read the full file on GitHub · 70 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. 5d ago First seen · 70 lines · 25 tokens per session scan A c56e1770f0c0

Subscribe to this mod's changes

localization is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 740 once invoked, about $0.0001 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 2026-08-31.