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.
git clone --depth 1 https://github.com/hamzafarooq/claude-code-starterWrote 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/commands/hamzafarooq/claude-code-starter/youtube-researcher)<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/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/commands/hamzafarooq/claude-code-starter/youtube-researcher"><img src="https://agentmods.dev/badge/commands/hamzafarooq/claude-code-starter/youtube-researcher.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 | $0.00000 | $0.00417 |
| Opus 5.5 | $0.00000 | $0.00167 |
| Sonnet 5.5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
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 2mo 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.
What it actually says
If a topic was not provided, ask the user:
- What topic or question they want to research
- How many videos they want (default: 5)
- Any preferences — e.g. recent only, beginner-friendly, a specific channel
Then:
- 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+) - Take a snapshot to read the search results —
mcp__brave-devtools__browser_snapshot - If results look thin or off-topic, refine the query and try once more
- 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
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.
- 2mo ago First seen · 44 lines · 0 tokens per session scan A bece7c8a439d
youtube-researcher is a command published in the GitHub repository hamzafarooq/claude-code-starter (150 stars, last pushed 26d 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.
youtube-researcher compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youtube-researcherhamzafarooq/claude-code-starter | Command | 150 | 26d ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |