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 fortunto2/solo-factory --skill i18ngit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote 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/fortunto2/solo-factory/i18n)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/i18n"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/i18n/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/skills/fortunto2/solo-factory/i18n"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/i18n.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 | $0.00044 | $0.02670 |
| Opus 5 | $0.00022 | $0.01335 |
| Sonnet 5 | $0.00009 | $0.00534 |
| Haiku 4.5 | $0.00004 | $0.00267 |
Grade A, and why
solo-i18n 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/i18n
Take an app from one language to many, and keep it there. Written after shipping 36 languages in an iOS app; the traps below each cost real time and none of them announce themselves — a missed string looks perfect in English.
The order of work
- Humanize the source language first. Translating is per-language cost:
fixing an English sentence after the fact means re-translating it in every
language.
/humanizeon the long copy, then translate. - Extract, don't hunt. Get the platform's extractor to produce the key list. A grep for quoted strings finds prose and misses everything typed wrong (see the type rule below).
- Translate in batches, machine-first, with a validator that refuses a batch dropping a format specifier or a plural category.
- Look at it running, in a right-to-left language and in a long-word language (German, Finnish). A language that is merely declared is not a language that works.
The type rule — the one that decides everything
Anything a person reads must be typed as the platform's localizable type, not as a plain string.
| Platform | Right | Wrong, and silent |
|---|---|---|
| SwiftUI | LocalizedStringKey, LocalizedStringResource |
let title: String |
| React / Next | t("key") from the i18n hook |
a bare JSX literal in a prop |
| Android Compose | stringResource(R.string.x) |
a String constant |
The extractor only sees literals in positions typed as localizable. A view
property declared let title: String takes its literal from the call site,
where nothing is looking — the control is never translated and English still
looks perfect. One pass found the whole bottom tab bar, four gallery filters,
four calendar chips, the settings list and every icon button's screen-reader
name, all invisible until somebody switched language.
Put it in the pre-commit hook. A lint rule on the naming that means "this is
shown" (title, label, note, blurb, caption, placeholder) typed as
a plain string catches it while it is one line, not one release.
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 · 218 lines · 44 tokens per session scan A d85422465284
solo-i18n is a skill published in the GitHub repository fortunto2/solo-factory (18 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,670 once invoked, about $0.0002 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.
Other skills, from other repositories
website-maintainer
Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.
comet-bilingual-docs
A workflow for keeping Comet documentation in Chinese and English aligned across READMEs, skills, release notes, and website pages. It preserves confirmed wording, repository structure, examples, commands, links, and configuration names.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
humanize-korean
A Korean editing tool that removes translation-like phrasing and common AI writing habits while preserving facts, numbers, names, and quotations. It is intended for existing Korean prose, not for writing new marketing copy.
zh-tw
Rewrite the previous reply in Traditional Chinese.
humanize-korean
A tool for rewriting Korean prose so it sounds more naturally written by a person while preserving its meaning, tone, facts, protected text, and evidence. It targets translation-like wording, repetitive endings, and formulaic AI-style phrasing.