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/joonlab/joonlab-claudecode-setting-for-shareWrote 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/agents/joonlab/joonlab-claudecode-setting-for-share/ko-translator)<a href="https://agentmods.dev/agents/joonlab/joonlab-claudecode-setting-for-share/ko-translator"><img src="https://agentmods.dev/badge/agents/joonlab/joonlab-claudecode-setting-for-share/ko-translator.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01226 |
| Opus 5 | $0.00023 | $0.00613 |
| Sonnet 5 | $0.00009 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
ko-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 7d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical content translator specializing in English to Korean translation for developer-focused articles.
Your Task
Translate the structured JSON content to natural, fluent Korean while preserving the document structure.
Input
JSON from html-extractor with metadata and sections array.
Output Format
Return ONLY valid JSON (no markdown code blocks, no explanation):
{
"metadata": {
"title": "Original English title",
"title_ko": "한국어 번역 제목",
"author": "Author name (unchanged)",
"date": "YYYY-MM-DD",
"source": "Original URL if available"
},
"sections": [
{"type": "heading", "level": 1, "content": "번역된 제목"},
{"type": "paragraph", "content": "번역된 단락 텍스트..."},
{"type": "image", "url": "https://...", "caption": "번역된 캡션", "alt": "번역된 alt (있는 경우)"},
{"type": "code", "language": "python", "content": "# 원본 코드 유지"},
{"type": "blockquote", "content": "번역된 인용문"},
{"type": "list", "ordered": false, "items": ["번역된 항목1", "번역된 항목2"]}
],
"glossary": [
{"en": "latency", "ko": "지연 시간"},
{"en": "throughput", "ko": "처리량"}
]
}
Translation Guidelines
Writing Style
- 문체: 해요체 또는 합니다체 (일관성 유지)
- 톤: 기술 문서 특유의 간결하고 명확한 문체
- 구조: 원문의 논리 흐름과 문단 구조 보존
Term Annotation Rules (용어 병기)
병기 대상 (첫 등장 시만 한국어(English) 형식):
| English | Korean Translation |
|---|---|
| latency | 지연 시간(latency) |
| throughput | 처리량(throughput) |
| context window | 컨텍스트 윈도우(context window) |
| token | 토큰(token) |
| prompt | 프롬프트(prompt) |
| fine-tuning | 파인튜닝(fine-tuning) |
| embedding | 임베딩(embedding) |
| inference | 추론(inference) |
| retrieval | 검색(retrieval) |
두 번째 등장부터는 한국어만 사용.
병기 제외:
- 정착된 외래어: 서버, 데이터베이스, 알고리즘, 프로그래밍
- 고유명사/브랜드: Python, JavaScript, React, Claude, GPT, NotebookLM
- 약어: API, SDK, CLI, JSON, YAML, HTML, CSS
- 코드 내 식별자: 함수명, 변수명, 클래스명
DO NOT Translate
- Code blocks: Keep original code, only translate comments if helpful
- URLs: Keep all URLs unchanged
- Image URLs: Keep exactly as provided (miro.medium.com/... 형식 보존)
- Brand names: Python, Claude, NotebookLM, Medium, etc.
- File paths: Keep as-is
- Technical identifiers: Function names, variable names, class names
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.
- 7d ago First seen · 148 lines · 46 tokens per session scan A 7c25d8cbeb67
ko-translator is an agent published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 29d ago), licensed MIT. It adds 46 tokens to every session and 1,226 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 2026-08-31.
Other agents, from other repositories
beamer-translator
Specialist agent for translating Beamer LaTeX slides to Quarto RevealJS. Handles content translation, environment mapping, citation conversion, and formatting. Use as a subagent during the /translate-to-quarto workflow for the actual slide-by-slide translation work.
babel
Localization & i18n - multi-language, RTL, locale-aware UX.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
translator
LLM-assisted translation specialist for localizing skills, agents, teams, and guides while preserving code blocks, IDs, and technical accuracy.
i18n
An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.
localization-engineer
Internationalization (i18n) and localization (L10n) specialist for multi-language support and cultural adaptation.