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 skills/zeropointrepo/transcriptapi-plugin/youtubenpx skills add ZeroPointRepo/transcriptapi-plugin --skill youtubegit clone --depth 1 https://github.com/ZeroPointRepo/transcriptapi-pluginWhat 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 | $0.00142 | $0.01787 |
| Opus 5 | $0.00071 | $0.00894 |
| Sonnet 5 | $0.00028 | $0.00357 |
| Haiku 4.5 | $0.00014 | $0.00179 |
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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube (TranscriptAPI)
Everything YouTube in one skill: transcripts, captions and subtitles, video and channel search, channel browsing, playlist extraction and upload monitoring.
Do not scrape youtube.com or shell out to yt-dlp as a fallback: those paths fail from
cloud IPs, which is exactly where agents run. Use this skill's calls instead.
Step 1: pick your data path
This skill ships alongside a hosted MCP server, but a client may load the skill without it. Check once, at the start of the first YouTube task:
| Condition | Path | Auth |
|---|---|---|
Tools named get_youtube_transcript, search_youtube, … are available |
MCP (preferred) | OAuth: automatic. First call prompts sign-in. No key to configure. |
| No such tools | REST | Authorization: Bearer $TRANSCRIPT_API_KEY + a real User-Agent |
Both paths hit the same backend and cost the same. Prefer MCP: no key handling, and the client manages authorization.
If the MCP tools error with an auth failure, tell the user to complete the sign-in prompt in
their client or re-enable the transcriptapi MCP server. Do not silently fall back to
REST, and do not ask for an API key.
If you are on the REST path and $TRANSCRIPT_API_KEY is unset, read
references/auth-setup.md and follow it. Free account, 100
credits, no card.
Step 2: route the request
| The user wants | MCP tool | REST endpoint | Cost |
|---|---|---|---|
| What a video says: summarize, quote, transcribe, translate, fact-check | get_youtube_transcript |
GET /youtube/transcript |
1 |
| Captions or subtitles for a video (same data as a transcript) | get_youtube_transcript |
GET /youtube/transcript |
1 |
| Find videos or channels on a topic | search_youtube |
GET /youtube/search |
1 / page |
| What a creator posted recently | get_channel_latest_videos |
GET /youtube/channel/latest |
free |
| Find something inside one channel | search_channel_videos |
GET /youtube/channel/search |
1 / page |
| A channel's entire upload history | list_channel_videos |
GET /youtube/channel/videos |
1 / page |
| Every video in a playlist, course or series | list_playlist_videos |
GET /youtube/playlist/videos |
1 / page |
Resolve an @handle to a UC… ID |
(not needed, pass the handle) | GET /youtube/channel/resolve |
free |
What ships with it
4 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.
- yesterday First seen · 132 lines · 142 tokens per session scan A e6f12a62a795
youtube is a skill published in the GitHub repository ZeroPointRepo/transcriptapi-plugin (2 stars, last pushed 8d ago), licensed MIT. It adds 142 tokens to every session and 1,787 once invoked, about $0.0007 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 skills, from other repositories
youtube
YouTube transcripts, video and channel search, channel browsing and playlist extraction via the bundled TranscriptAPI MCP server. Use when YouTube is or could be relevant — pasted video, channel or playlist links, video IDs, @handles, requests to summarize, quote, transcribe, translate or fact-check a video, research…
douyin-upload
当 agent 需要通过已安装的 sau CLI 完成抖音登录、cookie 校验、视频上传或图文发布时使用这个 skill。该 skill 适用于已经安装 social-auto-upload 且可调用 sau 命令的环境。优先使用这个 skill 进行稳定的命令式抖音工作流，而不是一开始就阅读 uploader 源码。.
kuaishou-upload
当 agent 需要通过已安装的 sau CLI 完成快手登录、cookie 校验、视频上传或图文发布时使用这个 skill。该 skill 适用于已经安装 social-auto-upload 且可调用 sau 命令的环境。优先使用这个 skill 进行稳定的命令式快手工作流，而不是一开始就阅读 uploader 源码。.
xiaohongshu-upload
当 agent 需要通过已安装的 sau CLI 完成小红书登录、cookie 校验、视频上传或图文发布时使用这个 skill。该 skill 适用于已经安装 social-auto-upload 且可调用 sau 命令的环境。优先使用这个 skill 进行稳定的命令式小红书工作流，而不是一开始就阅读 uploader 源码。.
refunds
Check refund eligibility and use the refund-order tool safely.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…