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 eat-pray-ai/yutu --skill youtubegit clone --depth 1 https://github.com/eat-pray-ai/yutuWrote 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/eat-pray-ai/yutu/youtube)<a href="https://agentmods.dev/skills/eat-pray-ai/yutu/youtube"><img src="https://agentmods.dev/badge/skills/eat-pray-ai/yutu/youtube/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/eat-pray-ai/yutu/youtube"><img src="https://agentmods.dev/badge/skills/eat-pray-ai/yutu/youtube.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00986 |
| Opus 5.5 | $0.00019 | $0.00394 |
| Sonnet 5.5 | $0.00010 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
youtube 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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube
Manage YouTube resources via MCP tool calls — abuseReport, activity, caption, channel, channelBanner, channelSection, comment, commentThread, i18nLanguage, i18nRegion, liveBroadcast, liveChatBan, liveChatMessage, liveChatModerator, liveStream, member, membershipsLevel, playlist, playlistImage, playlistItem, search, subscription, superChatEvent, thirdPartyLink, thumbnail, video, videoAbuseReportReason, videoCategory, watermark.
Key Principles
- Confirm before deleting: Always list exactly what will be deleted and get explicit user confirmation before calling any destructive tool.
- Verify targets: Before modifying or deleting, use a read tool to confirm the resource exists and matches the user's intent.
- Preserve existing data: When updating resources, only modify fields the user explicitly asked to change.
- Report resource IDs: Always include resource IDs in responses so the user can reference them.
Tools
Read (safe, no side effects)
activity-listcaption-downloadcaption-listchannel-listchannelSection-listcomment-listcommentThread-listi18nLanguage-listi18nRegion-listliveBroadcast-listliveChatMessage-listliveChatModerator-listliveStream-listmember-listmembershipsLevel-listplaylist-listplaylistImage-listplaylistItem-listsearch-listsubscription-listsuperChatEvent-listthirdPartyLink-listvideo-getRatingvideo-listvideoAbuseReportReason-listvideoCategory-list
Write (create or update content)
abuseReport-insertcaption-insertcaption-updatechannel-updatechannelBanner-insertcomment-insertcomment-markAsSpamcomment-setModerationStatuscomment-updatecommentThread-insertliveBroadcast-bindliveBroadcast-insertliveBroadcast-insertCuepointliveBroadcast-transitionliveBroadcast-updateliveChatBan-insertliveChatMessage-insertliveChatMessage-transitionliveChatModerator-insertliveStream-insertliveStream-updateplaylist-insertplaylist-updateplaylistImage-insertplaylistImage-updateplaylistItem-insertplaylistItem-updatesubscription-insertthirdPartyLink-insertthirdPartyLink-updatethumbnail-setvideo-insertvideo-ratevideo-reportAbusevideo-updatewatermark-set
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 123 lines · 48 tokens per session scan A 6568c450188f
youtube is a skill published in the GitHub repository eat-pray-ai/yutu (706 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 986 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 2026-08-30.
Other skills, from other repositories
rad-migrate
Migrate a YouTube channel to Rad TV — download in HD and publish with metadata, thumbnails, and an ordered playlist. Use when someone wants to move, copy, back up, or republish a YouTube channel to Rad TV, or asks about rad-migrate, HD download quality caps, YouTube bot checks, PO tokens, or failed Rad transcodes.
youtube-content
YouTube Data API — search, video details, channel info, transcripts.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.
octo-html
HTML docs domain (octo-doc) — create and govern self-contained interactive HTML documents, immutable versions, drafts, sharing, media, comments, and agent element edits. Bots cannot delete documents. This is a DIFFERENT backend from the octo-docs (CRDT/Yjs) domain. Load after octo-shared.
octo-shared
Shared knowledge for using the octo CLI — authentication, unified gateway config, output envelopes, universal flags, error handling, and common patterns. Load before invoking any octo domain skill.
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.