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 roshaw/claude-translation-agency --skill translate-initgit clone --depth 1 https://github.com/roshaw/claude-translation-agencyWrote 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/roshaw/claude-translation-agency/translate-init)<a href="https://agentmods.dev/skills/roshaw/claude-translation-agency/translate-init"><img src="https://agentmods.dev/badge/skills/roshaw/claude-translation-agency/translate-init/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/roshaw/claude-translation-agency/translate-init"><img src="https://agentmods.dev/badge/skills/roshaw/claude-translation-agency/translate-init.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 | $0.00178 | $0.02587 |
| Opus 5.5 | $0.00071 | $0.01035 |
| Sonnet 5.5 | $0.00036 | $0.00517 |
| Haiku 4.5 | $0.00018 | $0.00259 |
Grade A, and why
translate-init 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
translate-init
A guided wizard that builds translation.config.json at the root of the project being
translated (the target project — the folder with the source files) and registers that folder as a
tracked project. It asks about each option one step at a time, explaining what the option does and
what to put, and pre-fills what it can detect. Run it once per project, then run /translate.
Placement is the whole point. The file goes in the target project, not in the Translation Agency toolkit folder. Pointing at
C:\Projects\MyAppwritesC:\Projects\MyApp\translation.config.json.
Invocation
/translate-init # set up the current folder as the target project
/translate-init --path <dir> # set up a specific project, e.g. --path C:\Projects\MyApp
/translate-init <path> # shorthand for --path
Step 0 — Resolve the target project root
--path / bare <path> → that folder; else the current directory (accept an absolute computer path
as given). This root is where the config is written. If a translation.config.json already
exists, read it and offer to update it (its current values become the defaults) — never silently
clobber.
Step 1 — Detect, so defaults are pre-filled (don't ask what you can infer)
Using Glob/Grep/Read (never shell loops), infer: source language (messages.en.ts, en/,
.en.md, -en.po, or a content sample; default en); existing target languages already present;
formats present (JS/TS or JSON catalogs, WordPress .pot/.po, i18next/.arb, MD/MDX/HTML
trees, subtitles, CSV); a likely include set (where translatable files actually live); a
verify command (npx tsc --noEmit if there's a tsconfig); and any WordPress text domain.
Print a short "here's what I found" summary before asking anything.
Step 2 — Walk the operator through each option (the guided part)
Ask about the settings one at a time, each with a one-line explanation of what it controls and
what to enter, and the detected value pre-filled as the default. Use AskUserQuestion (batching a few
related ones per screen is fine), but always include the explanation so the operator understands the
choice. If the session is unattended, skip the prompts, use detected defaults + general +
inplace + first-run research + report queries, and state the assumptions.
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 · 150 lines · 178 tokens per session scan A f3c3d9c1d5b9
translate-init is a skill published in the GitHub repository roshaw/claude-translation-agency (2 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 2,587 once invoked, about $0.0007 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 skills, from other repositories
internationalization
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled…
deutsch-englisch-digitale-inhalte-handbuch
Für Deutsch Englisch AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Schnittstellenkarte mit Zuständigkeits- und Nachweisfragen. Fachgebiet: AGB-Recht-Prüfer. Route: deutsch-englisch-digitale-inhalte-handbuch.
deutsch-englisch-agb
Für Deutsch Englisch AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Schnittstellenkarte mit Zuständigkeits- und Nachweisfragen. Fachgebiet: AGB-Recht-Prüfer. Route: deutsch-englisch-agb.
rtl-internationalization
Right-to-left (RTL) layout and bidirectional text support for Hebrew, Arabic, Persian, and Urdu interfaces. Use when building UI that must support RTL languages, converting physical CSS/Tailwind properties to logical ones, handling mixed-direction (bidi) text, mirroring directional icons, or testing an app with…
localization-l10n
Implement localization (l10n) best practices to adapt applications for specific regions, languages, and cultural preferences.
internationalization-i18n
Implement internationalization (i18n) best practices for web and mobile applications to support multiple languages and locales.