youtube-to-knowledge: Command for Claude Code

.claude/commands/video_specialist.md

video_specialist is a command for Claude Code from velmighty/youtube-to-knowledge. It costs 0 tokens per session (194 once invoked), scanned A, original, MIT.

A video-analysis helper for answering detailed questions about processed videos using their transcripts. A transcript is a written record of what was said, and enriched transcripts may include timestamps and speaker labels.

In plain words
What is it for?
Use it to find exact claims, strategies, examples, numbers, timestamps, and speaker positions in one or more videos, and to compare what different speakers said.
Why use it?
It checks the source transcript instead of relying only on a summary, reducing the risk of missing details or inventing claims. It can show where statements occurred and who said them when that information exists.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is velmighty/youtube-to-knowledge's own configuration. It tells Claude Code how to work on youtube-to-knowledge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything youtube-to-knowledge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to velmighty/youtube-to-knowledge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/velmighty/youtube-to-knowledge/main/.claude/commands/video_specialist.md
Clone the repo
git clone --depth 1 https://github.com/velmighty/youtube-to-knowledge

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 video_specialist

README.md
[![agentmods](https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/video_specialist/github.svg)](https://agentmods.dev/commands/velmighty/youtube-to-knowledge/video_specialist)
Your own site
<a href="https://agentmods.dev/commands/velmighty/youtube-to-knowledge/video_specialist"><img src="https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/video_specialist/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.

agentmods 80×15 button for video_specialist

Your own site · 80×15
<a href="https://agentmods.dev/commands/velmighty/youtube-to-knowledge/video_specialist"><img src="https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/video_specialist.svg" alt="Reviewed on agentmods" width="80" 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 194 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 $0.00194
Opus 5 $0.00000 $0.00097
Sonnet 5 $0.00000 $0.00039
Haiku 4.5 $0.00000 $0.00019

Measured 10d ago against content hash 294e16f4a6b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

video_specialist 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 10d 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/video_specialist.md · 19 lines

What it actually says

Deep-dive analyst for processed video content. Use to answer specific questions about what was said, strategies mentioned, or claims made in a video.

Data sources (priority order)

  1. vault/content/<channel>/raw/transcript_enriched.txt — timestamps + optional speaker labels
  2. vault/content/<channel>/raw/transcript_raw.txt — plain text fallback
  3. vault/content/<channel>/summary.md — for overview questions only

Rules

  • Always read the transcript, not just the summary.
  • Quote with timestamps when enriched transcript is available.
  • Attribute claims to specific speakers when diarization data exists.
  • List strategies step-by-step with concrete examples from the video.
  • For data points, give exact numbers from the transcript.
  • If the transcript doesn't contain the answer, say so clearly — never fabricate.

Multi-video queries

  • Read each relevant transcript separately.
  • Compare positions across speakers; note agreements and contradictions.
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. 10d ago First seen · 19 lines · 0 tokens per session scan A 294e16f4a6b2

Subscribe to this mod's changes

video_specialist is a command published in the GitHub repository velmighty/youtube-to-knowledge (59 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 194 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.