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.
npx skills add ofcskn/mobile-automation-plugin --skill managing-app-localizationsgit clone --depth 1 https://github.com/ofcskn/mobile-automation-pluginWrote 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.
[](https://agentmods.dev/skills/ofcskn/mobile-automation-plugin/managing-app-localizations)<a href="https://agentmods.dev/skills/ofcskn/mobile-automation-plugin/managing-app-localizations"><img src="https://agentmods.dev/badge/skills/ofcskn/mobile-automation-plugin/managing-app-localizations.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.00598 |
| Opus 5 | $0.00042 | $0.00299 |
| Sonnet 5 | $0.00017 | $0.00120 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
managing-app-localizations 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 6d 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.
What it actually says
Managing App Localizations
When to use
| Request | Action |
|---|---|
| "add a language" | Add locale to config, create locale JSON, create metadata folders |
| "fix missing translations" | Run validate-translations.js, fill missing keys |
| "audit all locales" | Run validate-translations.js without a locale filter |
| "translate strings" | Copy en.json, fill values, validate |
File structure
.msd/locales/{app-id}/
├── en.json ← Source of truth — all keys must be here
├── tr.json ← All keys from en.json, values in Turkish
└── de.json ← All keys from en.json, values in German
Steps — Add a new locale
- Confirm locale codes:
skills/managing-app-localizations/references/locale-codes.md - Copy source:
cp .msd/locales/{appId}/en.json .msd/locales/{appId}/{i18next-code}.json - Translate all values in the new file (never translate
{{variable}}placeholders) - Validate:
node skills/managing-app-localizations/scripts/validate-translations.js {appId} - Create metadata folders:
mkdir -p .msd/metadata/{appId}/ios/{ios-locale}mkdir -p .msd/metadata/{appId}/android/{play-locale}
- Copy metadata from
en-US/and translate each.txtfile - Validate metadata:
node skills/managing-store-metadata/scripts/validate-metadata.js {appId} - Add locale to
.msd/config/{appId}.config.json→locales[]array - For RTL locales (ar, he, fa, ur): note that
I18nManager.forceRTL(true)is required in app startup
Rules
- Never translate
{{variable}}or${variable}placeholders in translation strings - Batch max 50 keys per AI translation call for quality control
- Avoid machine-only translation for Turkish, Arabic, Japanese — quality suffers
- Provide app glossary/context to translators for brand terms
- validate-translations.js exits 1 if any source key is missing in any locale
Reference
Load on demand: skills/managing-app-localizations/references/locale-codes.md
What ships with it
2 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.
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.
- 6d ago First seen · 55 lines · 83 tokens per session scan A ddfa86f45a1c
managing-app-localizations is a skill published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 598 once invoked, about $0.0004 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.
Other skills, from other repositories
cn-android-flavor
A release guide for the China-market Android version of a Flutter app. It covers China-based services such as JPush, WeChat, Alipay, and content moderation, while requiring the app to exclude Google services and follow local app-name and data-collection rules.
flutter-coding-conventions
A set of shared engineering rules for Flutter apps, including folder layout, app state, navigation, data models, languages, and version tracking. It is intended as a starting standard for Flutter and NestJS projects.
kappmaker-aso-metadata
Write the per-locale App Store metadata for a KAppMaker app — name, subtitle, keywords and description across locales, plus the rules that decide what goes where: no word repeated within a locale, uniqueness across locales, and quality over uniqueness. Use when the user asks what to call the app in the stores, or to…
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
asc-localize-metadata
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.