youtube-researcher

youtube-researcher is a command for Claude Code from hamzafarooq/claude-code-starter. It costs 0 tokens per session (417 once invoked), scanned A, original, MIT.

A command for researching videos on YouTube, a website for watching and publishing videos. It searches for videos on a supplied topic and summarizes the results in a table.

In plain words
What is it for?
Use it to find several videos about a topic, compare their channels, view counts, dates, and links, and select a useful first watch.
Why use it?
It organizes scattered search results into a short comparison. It helps you see which video is a sensible starting point and what kind of coverage exists.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to find several videos about a topic, compare their channels, view counts, dates, and links, and select a useful first watch.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hamzafarooq/claude-code-starter/youtube-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/hamzafarooq/claude-code-starter

Made for: Claude Code.

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 youtube-researcher

README.md
[![agentmods](https://agentmods.dev/badge/commands/hamzafarooq/claude-code-starter/youtube-researcher.svg)](https://agentmods.dev/commands/hamzafarooq/claude-code-starter/youtube-researcher)
Your own site
<a href="https://agentmods.dev/commands/hamzafarooq/claude-code-starter/youtube-researcher"><img src="https://agentmods.dev/badge/commands/hamzafarooq/claude-code-starter/youtube-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00000 $0.00417
Opus 5 $0.00000 $0.00209
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00042

Measured 8d ago against content hash bece7c8a439d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

youtube-researcher 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 8d 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.

.claude/commands/youtube-researcher.md · 44 lines

What it actually says

If a topic was not provided, ask the user:

  1. What topic or question they want to research
  2. How many videos they want (default: 5)
  3. Any preferences — e.g. recent only, beginner-friendly, a specific channel

Then:

  1. Use Brave MCP to navigate to YouTube search — mcp__brave-devtools__browser_navigate — using the URL format: https://www.youtube.com/results?search_query=TOPIC (replace spaces with +)
  2. Take a snapshot to read the search results — mcp__brave-devtools__browser_snapshot
  3. If results look thin or off-topic, refine the query and try once more
  4. Close the browser when done — mcp__brave-devtools__browser_close

Produce the following write-up directly — no preamble:

YouTube Research: [Topic]

Search query used: [exact query]


# Title Channel Views Published Link
1 ... ... ... ... Watch
2 ... ... ... ... Watch

Top pick

[Video title] — One sentence on why this is the best starting point for a PM or non-technical person.

What the results tell you

2-3 sentences on the overall landscape: Is this topic well-covered? Are results mostly technical or beginner-friendly? Any dominant voices or channels worth following?

Suggested follow-up searches

2-3 alternative queries to go deeper on subtopics.


Rules:

  • Use plain English throughout
  • Do not fabricate view counts or dates — only report what you read from the page
  • If YouTube blocks the search or returns no results, tell the user clearly and stop
  • After the write-up, ask: "Want me to save this to docs/youtube-research.md?"

$ARGUMENTS

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. 8d ago First seen · 44 lines · 0 tokens per session scan A bece7c8a439d

Subscribe to this mod's changes

youtube-researcher is a command published in the GitHub repository hamzafarooq/claude-code-starter (141 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 417 tokens. 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.