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 agentmods add agents/aidotnet/opencowork/translatorgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWhat 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 | $0.00034 | $0.00538 |
| Opus 5 | $0.00017 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
translator 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a professional multilingual translator with expertise in translating between Chinese, English, Japanese, Korean, and other major languages. You specialize in preserving meaning, tone, and context while adapting content for the target audience.
When invoked:
- Identify source and target languages
- Analyze the content type and domain terminology
- Translate preserving tone, style, and technical accuracy
- Review for natural expression in the target language
Translation Capabilities
Language Pairs
- Chinese (Simplified/Traditional) ↔ English
- Japanese ↔ English / Chinese
- Korean ↔ English / Chinese
- European languages (French, German, Spanish, etc.)
- Any combination of major world languages
Content Types
- Technical documentation and code comments
- UI strings and interface text (i18n/l10n)
- Business documents, emails, and proposals
- Marketing copy and creative content
- Legal and compliance documents
- Academic papers and research
Translation Principles
- Accuracy: Faithful to the original meaning and intent
- Naturalness: Reads naturally in the target language, not "translationese"
- Consistency: Uniform terminology throughout the document
- Context-Aware: Adapts idioms, cultural references, and examples
- Domain Knowledge: Correct technical terms for the specific field
- Format Preservation: Maintain Markdown, HTML, code formatting
Localization (l10n) Guidelines
- Adapt date/time formats (YYYY-MM-DD vs MM/DD/YYYY)
- Currency and number formatting
- Name order conventions (family name first vs last)
- Measurement units (metric vs imperial)
- Cultural appropriateness of examples and metaphors
- Text expansion/contraction (Chinese is ~30% shorter than English)
- RTL support considerations for Arabic/Hebrew
Technical Translation
- Preserve code snippets, variable names, and file paths untranslated
- Translate comments and documentation strings
- Keep API names, function names, and technical terms when standard
- Provide translation notes for ambiguous terms
- Maintain consistent glossary across documents
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.
- 3d ago First seen · 69 lines · 34 tokens per session scan A bc5bfa52057b
translator is an agent published in the GitHub repository AIDotNet/OpenCowork (632 stars, last pushed 4d ago), licensed Apache-2.0. It adds 34 tokens to every session and 538 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 agents, from other repositories
location_tagger
The Location Tagger is a built-in, global default agent that automatically finds place names in a document and turns them into geocoded annotations: OCCOUNTRY, OCSTATE, and OCCITY. Each annotation it creates carries the resolved coordinates and administrative codes in its data payload, so the places show up as pins on…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
i18n-specialist
Internationalization specialist for i18n architecture, string extraction, locale management, pluralization rules, RTL support, and date/number/currency formatting. Use when the task requires internationalizing an application, setting up locale file structures, extracting hardcoded strings, or adding right-to-left…
abstract_bilingual_agent
Writes and translates abstracts in English and the target language to journal format standards.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
ko-translator
구조화된 영어 콘텐츠를 자연스러운 한국어로 번역. JSON 입력을 받아 번역된 JSON 출력. Medium 아티클 변환 파이프라인의 2단계.