youtube-transcript

A command that downloads a transcript from a YouTube video and turns it into a question-oriented knowledge-graph note. A transcript is the written version of spoken video content, and a knowledge graph links related ideas and questions.

In plain words
What is it for?
Getting video metadata and English subtitles, saving the transcript, and synthesising it into a note when subtitles are available.
Why use it?
It saves the work of obtaining subtitles and turning a long video into structured notes.

Command

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.

agentmods
npx agentmods add commands/witt3rd/claude-plugins/youtube-transcript
Clone the repo
git clone --depth 1 https://github.com/witt3rd/claude-plugins
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 1,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01239
Opus 5 $0.00000 $0.00620
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured yesterday against content hash 9e4e22cc42f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

youtube-transcript 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 yesterday.

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.

plugins/azkg/commands/youtube-transcript.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Transcript and Create Note

Get transcript from a YouTube video using yt-dlp and create a comprehensive knowledge graph note using question-oriented content synthesis.

Usage

/youtube-transcript <youtube_url> [note_filename]

Process

Step 1: Content Acquisition (YouTube-Specific)

Extract video ID and metadata:

  • Parse video ID from YouTube URL
  • Use yt-dlp to get video metadata (title, description, uploader, upload date)
  • Command: yt-dlp --skip-download --write-info-json <url>

Get transcript using yt-dlp:

  • Use yt-dlp --write-auto-subs --sub-langs "en-US,en.*" --skip-download --sub-format vtt --convert-subs srt -o "attachments/%(id)s" <url>
  • This downloads English subtitles only, preferring en-US variant
  • Save transcript to attachments/<video_id>.srt or attachments/<video_id>.en.srt
  • If auto-generated subtitles unavailable, try manual subtitles with same --sub-langs flag
  • If transcript unavailable, inform user and suggest alternatives

Read the transcript:

  • Use Read tool to load transcript from attachments/<video_id>.srt
  • This is the raw content to be synthesized

Step 2: Universal Content Processing

Follow the shared content synthesis pipeline documented in _shared_content_synthesis.md:

  1. Apply Question-Oriented Content Synthesis

    • Phase 1: Central Question Discovery
    • Phase 2: Domain Question Extraction
    • Phase 3: Specific and Atomic Question Decomposition
    • Phase 4: Progressive Answer Development
  2. Generate note structure and metadata

    • Determine filename based on central question
    • Assign 3-6 tags mixing dimensions
    • Create YouTube-specific YAML frontmatter
  3. MOC Integration

    • Read TOPICS.md to understand MOC structure
    • Identify appropriate MOC(s) for this note
    • Update MOC file(s) with wikilink and description
  4. Relationship Discovery

    • Search for related notes in knowledge graph
    • Establish bidirectional relationships
    • Update related notes

Read the full file on GitHub · 159 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. yesterday First seen · 159 lines · 0 tokens per session scan A 9e4e22cc42f8

Subscribe to this mod's changes

youtube-transcript is a command published in the GitHub repository witt3rd/claude-plugins (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,239 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 2026-08-31.