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 tubealfred/mcp --skill youtube-video-researchgit clone --depth 1 https://github.com/tubealfred/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/tubealfred/mcp/youtube-video-research)<a href="https://agentmods.dev/skills/tubealfred/mcp/youtube-video-research"><img src="https://agentmods.dev/badge/skills/tubealfred/mcp/youtube-video-research/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/tubealfred/mcp/youtube-video-research"><img src="https://agentmods.dev/badge/skills/tubealfred/mcp/youtube-video-research.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 | $0.00046 | $0.00497 |
| Opus 5 | $0.00023 | $0.00249 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
youtube-video-research 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 12d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube video research with TubeAlfred
Use the hosted read-only MCP server at https://mcp.tubealfred.com/. Authenticate through OAuth when the client supports it, or use a TubeAlfred API key in a developer MCP client. TubeAlfred never modifies the user's YouTube account.
Choose the smallest useful workflow
- If the user supplied an unfamiliar YouTube URL, call
youtube_url_resolvebefore selecting another tool. - Call
youtube_video_getfor title, description, channel identity, publication time, duration, and public engagement metadata. - Call
youtube_video_transcriptonly when the task needs spoken content, quotations, timestamps, claims, chapters, or a content outline. - Call
youtube_related_videosonly when the user asks for competitors, adjacent topics, recommendation context, or follow-up ideas. - Call
youtube_channel_getonly when channel-level context changes the answer.
Do not use the deprecated youtube_video_transcript_full compatibility alias for new work.
Evidence discipline
- Separate video metadata from transcript statements and your own inference.
- Preserve transcript timestamps when citing a moment.
- State clearly when captions are unavailable, incomplete, translated, or auto-generated.
- Do not infer private analytics, revenue, audience identity, viewer journeys, or YouTube Studio retention from public data.
- Do not describe a missing transcript as a tool failure when TubeAlfred reports an unavailable-data outcome.
Pagination and retries
Related-video pages can return continuation tokens. Fetch another page only when the user's requested breadth requires it. Respect Retry-After on rate limits and transient failures. TubeAlfred tools are read-only, but repeated successful calls can still consume credits, so avoid speculative calls and duplicate retries.
Recommended output
Return a concise answer with:
- the video and channel identity;
- the evidence used, including transcript timestamps when applicable;
- the requested summary, brief, comparison, or extracted facts;
- any unavailable data or uncertainty;
- a short source list naming each TubeAlfred tool used.
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.
- 12d ago First seen · 43 lines · 46 tokens per session scan A c48f320f08db
youtube-video-research is a skill published in the GitHub repository tubealfred/mcp (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 497 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 skills, from other repositories
pake
Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…
odoo-agency-fleet-review
Review many client Odoo databases at once through odoo-mcp's cross-instance tools — fleet-wide accounting health, per-client aging, partial-failure triage — for agencies and partners managing 5–50 instances. Use when the user asks "which client...", "across all instances/databases", or wants a fleet/portfolio status.
odoo-data-quality-gate
Audit an Odoo database's data quality with evidence before trusting AI answers, importing, or migrating — duplicates, missing required values, orphaned references, format anomalies — and drive remediation through odoo-mcp's gated write workflow. Use when the user asks to "check data quality", "clean up data", "prepare…
odoo-migration-copilot
Plan and de-risk an Odoo version upgrade (16→17→18→19/20) using odoo-mcp's migration workbench — audit custom addons, classify upgrade-log failures into a worklist, resolve model renames, and preview JSON-2 payloads for the XML-RPC sunset. Use when the user mentions upgrading/migrating Odoo versions, broken upgrade…
odoo-month-end-close
Drive a month-end accounting close on Odoo through odoo-mcp — AR/AP aging, open-item and draft-invoice review, reconciliation checklists, and chatter documentation — with human sign-off at every posting step. Use when the user asks to "close the month", "review receivables/payables", "check aging", or prepare finance…
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…