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-extract)<a href="https://agentmods.dev/commands/sigistry/marketplace/i18n-extract"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/i18n-extract/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-extract"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/i18n-extract.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 | $0.00017 | $0.00909 |
| Opus 5.5 | $0.00007 | $0.00364 |
| Sonnet 5.5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
i18n-extract 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find the hardcoded user-facing strings in the components at $ARGUMENTS (or the current diff), extract them into the project's translation catalog, and replace each literal with the framework's idiomatic translation call. This is the tedious, error-prone part of an i18n retrofit that CLIs do badly, deciding what is actually user-facing, generating stable keys, and preserving interpolation. This command dispatches the i18n-extractor agent and reads the catalog-hygiene skill's framework conventions.
Process
Step 1: Detect the i18n framework and catalog layout
Read the manifest and existing catalog to learn the conventions (see the skill's references/catalog-frameworks.md):
| Framework | Signal | Call idiom | Catalog |
|---|---|---|---|
| react-i18next | i18next, useTranslation |
t('key'), <Trans> |
locales/<lng>/<ns>.json |
| react-intl / FormatJS | react-intl |
intl.formatMessage, <FormattedMessage> |
extracted .json per locale |
| vue-i18n | vue-i18n |
$t('key'), t('key') |
<lang>.json / messages |
| next-intl | next-intl |
useTranslations, t('key') |
messages/<locale>.json |
| i18next (vanilla) | i18next |
i18next.t('key') |
<lng>/translation.json |
| Angular i18n | @angular/localize, i18n= |
i18n attr / $localize |
messages.<locale>.xlf |
| gettext | .po/.pot, gettext, _() |
_('text'), ngettext |
<locale>/LC_MESSAGES/*.po |
If no i18n library is present, report that and propose one for the stack rather than inventing calls.
Step 2: Find hardcoded user-facing strings, and skip the rest
Scan JSX/template text nodes, alt/title/aria-label/placeholder attributes, and string literals passed to UI. Extract visible copy, button labels, headings, validation messages, and accessible-name attributes. Skip non-UI strings, object keys, enum values, URLs, routes, className/CSS, data-testid, console.*/logger messages, test fixtures, and code-only identifiers. When a string is ambiguous, mark it "review" rather than extracting blindly.
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 · 44 lines · 17 tokens per session scan A 0fc35f9aca88
i18n-extract is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 909 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
f5-lang
Set language preference for F5 Framework output.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
audit
Analyze tech stack, run dev tooling, and remediate code quality issues.
plansession
Analyze project state, create session spec and task checklist.
project-recap
Visual HTML project recap — current state, recent decisions, and cognitive debt hotspots.
compliance-fix
Show Qualimetry review findings for a file and apply the standards-compliant fix.