language_support_check

A command that checks whether every activated language has a human or AI translation for user-facing text and in-app documentation. It also finds hardcoded text that bypasses the translation system.

In plain words
What is it for?
Use it to audit translation files, dialogs, documentation, and hardcoded interface strings. It reports gaps but does not fill them unless the user explicitly confirms an AI backfill.
Why use it?
It reveals missing translations that a fallback to English might hide, helping teams find language gaps before release.

Command for Claude Code

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 commands/osiris-devworks/smart-citizen/language_support_check
Clone the repo
git clone --depth 1 https://github.com/Osiris-DevWorks/smart-citizen

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,488 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 $0.00021 $0.01488
Opus 5 $0.00010 $0.00744
Sonnet 5 $0.00004 $0.00298
Haiku 4.5 $0.00002 $0.00149

Measured 2d ago against content hash b8cc15b1d0e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

language_support_check 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.

.claude/commands/language_support_check.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/language_support_check

Audit translation coverage for every activated language. Catches the gaps the i18n fallback chain hides: a key that silently renders in English because it was never added to a language file, a new dialog whose strings were added to english/ui.json only, an in-app doc that never got a translated copy, and hardcoded literals that bypass tr() entirely and can never be translated.

Background: tr() resolves each key as ht (human translation), then at (AI translation), then the English base value, then the bare key. "Has at least the AI translation" means every key shows something in the selected language: ht or at non-empty. Provenance rules live in languages/TRANSLATIONS.md.

Policy constraints (read before drafting anything)

  • Never edit or overwrite a non-empty ht. Human translations are only ever replaced by better human translations.
  • AI backfill happens only at pre-release docs-sync time, with explicit confirmation. This command surfaces gaps; it does not fill them unless the user says so at the checkpoint.
  • New AI translations go in at (leave ht empty) so the inline provenance stays truthful and translators can find them with grep '"ht": ""'.

Inputs

  • languages/<lang>/ui.json for every activated language. Activated = what AppSettings.get_available_languages() (src/utils/settings.py) offers: English plus any folder whose ui.json carries at least one translation. languages/english/ui.json is the key universe; every leaf there is a key the UI can request.
  • languages/<lang>/HELP.md, ABOUT.md, LEGAL.md: per-language in-app docs, resolved by AppSettings.get_localized_doc_path(). A missing file falls back to the English docs/ copy.
  • languages/sources.json: per-language base.ini download URL for game strings.
  • installer.iss: the LanguageChoicePage option list and the selected_language registry write-back values.
  • src/gui/*.py: user-facing literals, to catch strings not routed through tr().
  • SmartCitizen.spec and scripts/build/build_exe.py: both bundling lists must ship the languages/ tree (a file present in the repo but missing from either list breaks only the frozen build).

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 21 tokens per session scan A b8cc15b1d0e6

Subscribe to this mod's changes

language_support_check is a command published in the GitHub repository Osiris-DevWorks/smart-citizen (99 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,488 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 2026-08-30.