yt-research

yt-research is a skill for Claude Code from aliildan/ytb-tools. It costs 78 tokens per session (969 once invoked), scanned A, original, MIT.

A workflow for researching many YouTube videos on one topic. It searches for videos, retrieves their transcripts, summarizes each one, and combines the results into a digest.

In plain words
What is it for?
Use it to survey videos about a keyword, compare many videos, or produce a combined research summary. You can choose how many videos and how detailed the summaries should be.
Why use it?
It removes the need to find, watch, transcribe, and summarize a large set of videos one by one.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the ytb-tools plugin — 1 skill, 3 commands, 1 MCP server shipped together

Good fit Use it to survey videos about a keyword, compare many videos, or produce a combined research summary. You can choose how many videos and how detailed the summaries should be.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aliildan/ytb-tools/yt-research
Install

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.

Any agent
npx skills add aliildan/ytb-tools --skill yt-research
Clone the repo
git clone --depth 1 https://github.com/aliildan/ytb-tools

Made for: Claude Code.

Or install ytb-tools, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

Wrote 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.

agentmods badge for yt-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/aliildan/ytb-tools/yt-research.svg)](https://agentmods.dev/skills/aliildan/ytb-tools/yt-research)
Your own site
<a href="https://agentmods.dev/skills/aliildan/ytb-tools/yt-research"><img src="https://agentmods.dev/badge/skills/aliildan/ytb-tools/yt-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00969
Opus 5 $0.00039 $0.00485
Sonnet 5 $0.00016 $0.00194
Haiku 4.5 $0.00008 $0.00097

Measured 7d ago against content hash 1a4398163498, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

yt-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 7d 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.

skills/yt-research/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube topic research (search → transcripts → summaries → digest)

This skill runs the full pipeline over many videos using the ytb-tools MCP tools (youtube_search, youtube_get_transcript, youtube_save_summary).

Inputs (parse from the user's request)

  • keyword (required) — the search query.
  • count (default 10) — how many videos to process (the "N").
  • depth (default quick) — quick | standard | detailed.
  • language (optional) — override the summary language (default = each video's language).

Steps

1. Search

Call youtube_search with query = keyword and limit = count. Report how many results actually came back (it may be fewer than requested — YouTube limits search depth).

2. Confirm before large runs

If the result count is greater than 20, STOP and confirm with the user before continuing — tell them exactly how many videos will be fetched and summarized and that it will take time and tokens. Wait for a yes. Skip this confirmation only if the user already explicitly approved a large run in their request (e.g. "yes, summarize all 150").

3. Fetch + summarize in batches

Process the videos in batches of 10. For each batch:

  1. For each video, call youtube_get_transcript with the videoId.
    • If a video has no transcript (error), skip it and record it in a "skipped" list — do not abort the whole run.
  2. Summarize each fetched transcript at the chosen depth, in the transcript's language (or the language override). Pick the model by depth and dispatch a subagent (Task tool) per summary — run the batch's summaries in parallel:
    • quick → model haiku (claude-haiku-4-5): one-line TL;DR + 3–5 bullets.
    • standard → model sonnet (claude-sonnet-4-6): key points + takeaways.
    • detailed → model opus (claude-opus-4-8): chapters, themes, quotes. Each subagent receives the transcript fullText and returns only the summary.
  3. For each summary, call youtube_save_summary with videoId, the summary text, the style (= depth), title, video url, the model id, and language.
  4. After each batch, post a short progress line: Batch k/N done — M summarized, S skipped.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 7d ago First seen · 77 lines · 78 tokens per session scan A 1a4398163498

Subscribe to this mod's changes

yt-research is a skill published in the GitHub repository aliildan/ytb-tools (0 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 969 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens