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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/i18n-doctor)<a href="https://agentmods.dev/commands/sigistry/marketplace/i18n-doctor"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/i18n-doctor/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.
<a href="https://agentmods.dev/commands/sigistry/marketplace/i18n-doctor"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/i18n-doctor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.00780 |
| Opus 5 | $0.00010 | $0.00390 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
i18n-doctor 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the translation catalogs in $ARGUMENTS (or the project's detected locale directory) for the correctness and completeness problems that silently ship broken UI in non-default languages. This is a static audit, it cross-references the catalog files against the keys used in code. Load the catalog-hygiene skill for framework conventions and the icu-messageformat skill for ICU/plural validation.
Process
Step 1: Locate the catalogs and the source locale
Find the locale files and identify the source locale (usually en), the reference every other locale is measured against. Detect the format from the layout (locales/<lng>/<ns>.json, messages/<locale>.json, messages.<locale>.xlf, <locale>/LC_MESSAGES/*.po) and how keys map to code calls (see references/catalog-frameworks.md).
Step 2: Cross-reference code against catalogs
Grep the codebase for translation calls (t('...'), formatMessage({ id: '...' }), $t('...'), _('...'), i18n= ids) and diff the key set against each catalog:
| Check | How to find it | Impact |
|---|---|---|
| Missing keys | Key used in code, absent in a locale | Runtime fallback or raw key shown to users |
| Unused keys | Key in catalog, referenced nowhere | Dead weight; translators paid to translate cruft |
| Untranslated values | Target value byte-equal to the source locale | Looks translated, ships English |
| Placeholder drift | {name}/{count} set differs across locales for one key |
undefined in the string, or a thrown formatter error |
| ICU syntax errors | Unbalanced {}, bad plural/select clause, unknown type |
Formatter throws or renders literally at runtime |
| Missing plural categories | Locale lacks a CLDR category its grammar requires (e.g. Polish few/many, Arabic zero/two) |
Wrong number agreement for real inputs |
Step 3: Validate ICU per locale
For every message with plural/selectordinal/select, parse the ICU (see the icu-messageformat skill) and confirm: the argument set matches the source, every branch is well-formed, and the locale supplies exactly the CLDR plural categories its language needs, not a copy of English's one/other (see references/pluralization-rules.md).
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.
- 12d ago First seen · 40 lines · 19 tokens per session scan A 8637efee144a
i18n-doctor is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 780 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.
Other commands, from other repositories
f5-lang
Set language preference for F5 Framework output.
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
review
Pressure-test an important decision, plan, proposal, strategy, architecture, or recommendation with adaptive depth and token-efficient verification.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.
compliance-fix
Show Qualimetry review findings for a file and apply the standards-compliant fix.