Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zgsm-ai/costrictnpx agentmods add skills/zgsm-ai/costrict/roo-translationWrote 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/zgsm-ai/costrict/roo-translation)<a href="https://agentmods.dev/skills/zgsm-ai/costrict/roo-translation"><img src="https://agentmods.dev/badge/skills/zgsm-ai/costrict/roo-translation/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/zgsm-ai/costrict/roo-translation"><img src="https://agentmods.dev/badge/skills/zgsm-ai/costrict/roo-translation.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 | $0.00070 | $0.01492 |
| Opus 5.5 | $0.00028 | $0.00597 |
| Sonnet 5.5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
roo-translation 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.
This is a copy
95% identical to roo-translation — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoStrict Translation Skill
When to Use This Skill
Use this skill when the task involves:
- Adding new translatable strings to the CoStrict extension
- Translating existing strings to new languages
- Updating or fixing translations in existing language files
- Understanding i18n patterns used in the codebase
- Working with localization files in either core extension or WebView UI
When NOT to Use This Skill
Do NOT use this skill when:
- Working on non-translation code changes
- The task doesn't involve i18n or localization
- You're only reading translation files for reference without modifying them
Supported Languages and Locations
Localize all strings into the following locale files: ca, de, en, es, fr, hi, id, it, ja, ko, nl, pl, pt-BR, ru, tr, vi, zh-CN, zh-TW
The VSCode extension has two main areas that require localization:
| Component | Path | Purpose |
|---|---|---|
| Core Extension | src/i18n/locales/ |
Extension backend strings |
| WebView UI | webview-ui/src/i18n/locales/ |
User interface strings |
Brand Voice, Tone, and Word Choice
For detailed brand voice, tone, and word choice guidance, refer to the guidance file:
This guidance file is loaded at runtime and should be consulted for the latest brand and style standards.
Voice, Style and Tone Guidelines
- Always use informal speech (e.g., "du" instead of "Sie" in German) for all translations
- Maintain a direct and concise style that mirrors the tone of the original text
- Carefully account for colloquialisms and idiomatic expressions in both source and target languages
- Aim for culturally relevant and meaningful translations rather than literal translations
- Preserve the personality and voice of the original content
- Use natural-sounding language that feels native to speakers of the target language
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 · 154 lines · 70 tokens per session scan A 3434bda9416b
roo-translation is a skill published in the GitHub repository zgsm-ai/costrict (4,462 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,492 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to roo-translation, differing in 42 lines, and is treated as a copy.
roo-translation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| roo-translationzgsm-ai/costrict | Skill | 4.5k | 1mo ago | Apache-2.0 | A | 70 | Claude Code, Codex |
| shapsynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 109 | Claude Code, Codex |
| rowansynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 115 | Claude Code, Codex |
| arboretosynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 66 | Claude Code, Codex |
| goal-calculator-repairzhnt/loushang | Skill | 2.0k | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |
| lastlight-evals-loopnearform/lastlight | Skill | 44 | 2d ago | MIT | A | 200 | Claude Code |
| issue-triagenearform/lastlight | Skill | 44 | 2d ago | MIT | A | 46 | Claude Code, Codex |