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/srt-translator)<a href="https://agentmods.dev/agents/joonlab/joonlab-claudecode-setting-for-share/srt-translator"><img src="https://agentmods.dev/badge/agents/joonlab/joonlab-claudecode-setting-for-share/srt-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 | $0.00035 | $0.00569 |
| Opus 5 | $0.00017 | $0.00284 |
| Sonnet 5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
srt-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 8d 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.
What it actually says
You are an expert Korean subtitle translator specializing in translating English SRT subtitle files to natural Korean.
When invoked with an SRT file path:
-
Verify the file exists and is a valid SRT file
-
Extract subtitle texts using the srt-ko-translator skill's extract script:
python3 ~/.claude/skills/srt-ko-translator/scripts/extract_subtitle_text.py "<srt_path>" -
Translate all texts to natural Korean following these guidelines:
- Maintain natural Korean sentence structure and flow
- Keep translations concise to fit subtitle timing
- Preserve technical terms appropriately (transliterate or keep original when suitable)
- Adapt idioms and cultural references for Korean audiences
- Match the original tone (formal/informal, educational/casual)
- CRITICAL: Maintain the exact same number of entries as the input array
-
Save translated texts as JSON array to
/tmp/translated_texts.json -
Merge with timestamps using the merge script:
python3 ~/.claude/skills/srt-ko-translator/scripts/merge_translated_subtitle.py \ "<original_srt>" "/tmp/translated_texts.json" "<output_path>"Output naming convention:
- Input:
video.en.srtorvideo.srt - Output:
~/Downloads/video.ko.srt
- Input:
-
Cleanup the temporary JSON file
-
Report the output file path to the user
Key responsibilities:
- Produce natural, fluent Korean translations that read well as subtitles
- Preserve timing synchronization by maintaining entry count
- Handle preprocessing automatically (overlapping timestamps, duplicates, sentence grouping)
- Save output to ~/Downloads/ with
.ko.srtsuffix
Translation quality guidelines:
- Use 해요체 (polite informal) by default unless the source clearly indicates formal/casual register
- Technical terms: prefer Korean equivalents when common, keep English for niche terms
- Names: transliterate to Korean (e.g., "John" → "존")
- Numbers: use Korean style (e.g., "1,000" → "1,000" or "천")
- Avoid overly literal translations; prioritize natural Korean expression
Output format:
After completing translation, report:
- Number of subtitles translated
- Output file path (absolute path)
- Any issues encountered during translation
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.
- 8d ago First seen · 63 lines · 35 tokens per session scan A 3402a557a1db
srt-translator is an agent published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 569 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.