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 brianshin22/youtube-translate-mcp --skill youtube-translategit clone --depth 1 https://github.com/brianshin22/youtube-translate-mcpWrote 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/brianshin22/youtube-translate-mcp/youtube-translate)<a href="https://agentmods.dev/skills/brianshin22/youtube-translate-mcp/youtube-translate"><img src="https://agentmods.dev/badge/skills/brianshin22/youtube-translate-mcp/youtube-translate/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/brianshin22/youtube-translate-mcp/youtube-translate"><img src="https://agentmods.dev/badge/skills/brianshin22/youtube-translate-mcp/youtube-translate.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 | $0.00050 | $0.00473 |
| Opus 5.5 | $0.00020 | $0.00189 |
| Sonnet 5.5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
youtube-translate 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 9d 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
YouTube Translate
Use the YouTube Translate tools for public YouTube videos. Do not claim a transcript exists unless a tool returned it.
Cached videos
Call get_transcript first for a transcript. A cached read costs 2,000 microcredits and returns immediately. The public demo endpoint, not the MCP tool, covers two example videos for free. Use include_timestamps=true when the user asks for timestamps, quotes, or specific moments.
Uncached videos
- Call
get_processing_quotefor the operation. - Show the user the maximum microcredit cost and the account balance. One million microcredits equals one US dollar.
- Ask for explicit approval before spending. Never guess a budget.
- If approved, call
start_videowithmax_credit_unitsequal to the quoted maximum. - Poll
get_video_status, then callget_transcript.
If the account has no credits, explain that the user must add prepaid credits at https://api.youtubetranslate.com/account/payments and approve a Stripe Link payment. Never ask for card or wallet credentials in chat.
Translation and subtitles
Use get_translation for translated text and get_subtitles for SRT or VTT. Use two-letter ISO language codes. Pass max_credit_units only after approval. Translation and subtitle formatting use the retained transcript, so they do not download the video again.
Summaries and search
Use get_summary with short, medium, or long. Use search_video to find a topic or quote; return its timestamp and surrounding passage.
Limits
Transcription is limited to 30 minutes of source audio. Translation and summary inputs are limited to 100,000 characters and 2,000 segments. If a tool returns a limit error, explain it instead of retrying blindly.
Privacy
Do not send private, confidential, or sensitive material to this service. Public-source media and results may be retained in a shared cache.
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.
- 9d ago First seen · 39 lines · 50 tokens per session scan A 1c25316f0451
youtube-translate is a skill published in the GitHub repository brianshin22/youtube-translate-mcp (5 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 473 once invoked, about $0.0002 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 2026-10-28.
youtube-translate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youtube-translatebrianshin22/youtube-translate-mcp | Skill | 5 | 9d ago | MIT | A | 50 | Claude Code, Codex |
| intl-expansionalirezarezvani/claude-skills | Skill | 29k | yesterday | MIT | A | 27 | Claude Code |
| azure-ai-translation-text-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 60 | Claude Code |
| chinese-documentationjnMetaCode/superpowers-zh | Skill | 8.5k | 11d ago | MIT | A | 62 | Claude Code |
| hardenfengshao1227/ccg-workflow | Skill | 6.0k | 4d ago | MIT | A | 62 | Claude Code |
| edit-sitemicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 104 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |