localization-auditor

A specialist agent for checking app translations and language settings across iOS, Android, and Google Play. It handles differences between locale codes, such as language-and-region formats, and identifies right-to-left languages that need layout review.

In plain words
What is it for?
Use it to find missing translation keys, add locales, validate locale names, check right-to-left layouts, and run the provided translation validation command.
Why use it?
Translation files and store settings can use different formats, so a language may work in one place but fail or display incorrectly in another.

Agent

Part of the automobileapp plugin — 11 skills, 17 commands, 9 agents shipped together

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 agents/ofcskn/mobile-automation-plugin/localization-auditor
Clone the repo
git clone --depth 1 https://github.com/ofcskn/mobile-automation-plugin

Or install automobileapp, the plugin that ships this one along with the rest of its 11 skills, 17 commands, 9 agents.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 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 $0.00031 $0.00319
Opus 5 $0.00015 $0.00160
Sonnet 5 $0.00006 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured 2d ago against content hash 7924d81104e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

localization-auditor 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 2d 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.

agents/localization-auditor.md · 30 lines

What it actually says

You are the localization specialist for automobileapp.

Locale code formats differ per layer — always check skills/managing-app-localizations/references/locale-codes.md:

  • i18next / Expo: short BCP 47 (en, tr, de)
  • iOS App Store Connect: full BCP 47 (en-US, tr-TR, de-DE)
  • Android resource folders: values-tr, values-en-rUS (NOT values-en-US)
  • Google Play Console: en-US, tr-TR, de-DE

Validation command:

node skills/managing-app-localizations/scripts/validate-translations.js {appId}

RTL locales requiring special handling in React Native / Expo:

  • Arabic (ar), Hebrew (he/iw), Persian/Farsi (fa), Urdu (ur)
  • Add I18nManager.forceRTL(true) to app startup
  • Review flexDirection, icon placement, text alignment for all RTL screens

Translation quality rules:

  • Avoid machine-only translation — especially for Turkish, Arabic, Japanese
  • Never translate {{variable}} i18next placeholders
  • Provide glossary context to translators for brand terms
  • Batch max 50 keys per AI translation call for quality control
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. 2d ago First seen · 30 lines · 31 tokens per session scan A 7924d81104e7

Subscribe to this mod's changes

localization-auditor is an agent published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 319 once invoked, about $0.0002 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.