A review of a SwiftUI app's text and translations. SwiftUI is Apple's framework for building app interfaces, and localization prepares those interfaces for different languages and regions.

Use it to check and fix localization in views, view models, models, managers, and app shortcut or watch-app translation files.

It finds user-facing text that is fixed in the code, untranslated, or otherwise likely to be missed before an international App Store release.

localize — Skill for Claude Code and Codex by mwd1234

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/mwd1234/ios-agentic-skills

agentmods

npx agentmods add skills/mwd1234/ios-agentic-skills/localize

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mwd1234/ios-agentic-skills/localize/github.svg)](https://agentmods.dev/skills/mwd1234/ios-agentic-skills/localize)

Your own site

<a href="https://agentmods.dev/skills/mwd1234/ios-agentic-skills/localize"><img src="https://agentmods.dev/badge/skills/mwd1234/ios-agentic-skills/localize/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mwd1234/ios-agentic-skills/localize"><img src="https://agentmods.dev/badge/skills/mwd1234/ios-agentic-skills/localize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,481 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.02481
Opus 5.5	$0.00018	$0.00992
Sonnet 5.5	$0.00009	$0.00496
Haiku 4.5	$0.00005	$0.00248

Measured 2mo ago against content hash 0c46960def1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localize 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 2mo 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.

.agent/skills/localize/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftUI Localization Audit

Perform a thorough localization audit of the SwiftUI codebase to identify and fix hardcoded strings that need to be localized.

When to use this skill

Before submitting to the App Store for international markets
After adding new UI features with user-facing text
When reviewing PRs that touch Views, ViewModels, or Models
When the user asks to check localization or translations

How to use it

Step 1: Pre-Flight Checks (All xcstrings Files)

Run localization status checks on all .xcstrings files upfront:

# iOS App
python3 scripts/check_localization_status.py YourApp/Localizable.xcstrings

# AppIntents (catches missing Siri shortcut translations early)
python3 scripts/check_localization_status.py YourApp/AppIntents/AppShortcuts.xcstrings

# Watch App
python3 scripts/check_localization_status.py "YourApp Watch App/Localizable.xcstrings"

Why AppIntents early? Missing shortcut keys cause Siri regressions that are hard to catch later.

Step 2: Scan Scope & Exclusions

Directories to scan:

Target	Directories
iOS App	`YourApp/Views/`, `YourApp/ViewModels/`, `YourApp/Models/`, `YourApp/Managers/`
Watch App	`YourApp Watch App/Views/`, `YourApp Watch App/ViewModels/`, `YourApp Watch App/Managers/`
AppIntents	`YourApp/AppIntents/`

Exclusions (always ignore):

# Use rg (ripgrep) with exclusions for all searches:
rg --type swift -g '!*Tests*' -g '!*UITests*' "PATTERN" <directory>

*Tests*/, *UITests*/ — Test code is not user-facing
Content inside #Preview { } blocks — Developer-only, stripped from production builds

Step 3: High Priority Pattern Audit

Search for these patterns using rg (faster than grep on macOS):

# Button labels
rg --type swift -g '!*Tests*' 'Button\("' YourApp/Views/ YourApp/ViewModels/ YourApp/Models/

# Label text
rg --type swift -g '!*Tests*' 'Label\("' YourApp/Views/ YourApp/ViewModels/ YourApp/Models/

# Navigation titles
rg --type swift -g '!*Tests*' '\.navigationTitle\("' YourApp/Views/

# Alert titles
rg --type swift -g '!*Tests*' '\.alert\("' YourApp/Views/

# TextField placeholders
rg --type swift -g '!*Tests*' 'TextField\("' YourApp/Views/

# Picker labels
rg --type swift -g '!*Tests*' 'Picker\("' YourApp/Views/

Read the full file on GitHub · 305 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.

2mo ago First seen · 305 lines · 46 tokens per session scan A 0c46960def1a

Subscribe to this mod's changes

localize is a skill published in the GitHub repository mwd1234/ios-agentic-skills (50 stars, last pushed 9mo ago), licensed MIT. It adds 46 tokens to every session and 2,481 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Localization Mobile

localize next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
localizemwd1234/ios-agentic-skills	Skill	50	9mo ago	MIT	A	46	Claude Code, Codex
flutter-setup-localizationflutter/agent-plugins	Skill	3.2k	2d ago	BSD-3-Clause	A	52	Claude Code
asc-localize-metadatarorkai/app-store-connect-cli-skills	Skill	1.1k	yesterday	MIT	A	60	Claude Code
asc-metadata-syncrorkai/app-store-connect-cli-skills	Skill	1.1k	yesterday	MIT	A	47	Claude Code
asc-in-app-eventsrorkai/app-store-connect-cli-skills	Skill	1.1k	yesterday	MIT	A	49	Claude Code
maui-localization-themingdotnet/maui-labs	Skill	235	yesterday	MIT	A	73	Claude Code, Codex
android-resourcesHoangNguyen0403/agent-skills-standard	Skill	583	today	MIT	A	59	Claude Code, Codex