youtube-transcribe-yt-dlp

youtube-transcribe-yt-dlp is a skill for Claude Code, Codex from supermaciz/sessions-chronicle. It costs 38 tokens per session (1,168 once invoked), scanned A, original, MIT.

A command-line method for extracting existing YouTube subtitles or captions as text using yt-dlp, a tool for working with online video metadata and files.

In plain words
What is it for?
Use it to list subtitle languages and save manual or automatically generated captions from YouTube URLs as text files.
Why use it?
It gets transcript text without downloading the video or audio and makes clear when subtitles are unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list subtitle languages and save manual or automatically generated captions from YouTube URLs as text files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp
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 supermaciz/sessions-chronicle --skill youtube-transcribe-yt-dlp
Clone the repo
git clone --depth 1 https://github.com/supermaciz/sessions-chronicle

Made for: Claude Code, Codex.

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-transcribe-yt-dlp

README.md
[![agentmods](https://agentmods.dev/badge/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp/github.svg)](https://agentmods.dev/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp)
Your own site
<a href="https://agentmods.dev/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp"><img src="https://agentmods.dev/badge/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp/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 youtube-transcribe-yt-dlp

Your own site · 80×15
<a href="https://agentmods.dev/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp"><img src="https://agentmods.dev/badge/skills/supermaciz/sessions-chronicle/youtube-transcribe-yt-dlp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,168 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 $0.00038 $0.01168
Opus 5 $0.00019 $0.00584
Sonnet 5 $0.00008 $0.00234
Haiku 4.5 $0.00004 $0.00117

Measured 12d ago against content hash 2e541166d03f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

youtube-transcribe-yt-dlp 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 12d 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/youtube-transcribe-yt-dlp/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Transcript with yt-dlp Only

Overview

Extract subtitle tracks from YouTube and produce transcript text files with yt-dlp only. Core principle: subtitle extraction only, never video/audio download, never browser automation.

When to Use

  • User asks for YouTube transcript, captions, subtitles, or subtitle-to-text export.
  • User provides one or more YouTube URLs (youtube.com/watch, youtu.be, youtube.com/shorts).
  • User wants a fast CLI workflow with yt-dlp.

When NOT to Use

  • User asks for full speech-to-text transcription from audio.
  • User asks to download video or audio files.
  • User requires browser automation tools.

Hard Rules

  • Use yt-dlp only.
  • Always include --skip-download.
  • Never use browser automation fallback.
  • Never download video/audio for transcription.
  • If subtitles are unavailable, report clearly and stop.

Quick Reference

Goal Command
List available subtitle languages yt-dlp --list-subs "<URL>"
Download manual + auto subs only yt-dlp --skip-download --write-subs --write-auto-subs --sub-langs "en.*,en" --sub-format "vtt" -o "%(title).180B [%(id)s].%(ext)s" "<URL>"
Restrict filename characters Add --restrict-filenames

Workflow

digraph youtube_transcript_flow {
  rankdir=TB;
  "Valid YouTube URL?" [shape=diamond];
  "Check yt-dlp available" [shape=box];
  "List subtitle tracks" [shape=box];
  "Any subtitle track available?" [shape=diamond];
  "Download subs with --skip-download" [shape=box];
  "Convert VTT/SRT to TXT" [shape=box];
  "Report output files" [shape=box];
  "Stop: explain limitation" [shape=box];

  "Valid YouTube URL?" -> "Check yt-dlp available" [label="yes"];
  "Valid YouTube URL?" -> "Stop: explain limitation" [label="no"];
  "Check yt-dlp available" -> "List subtitle tracks";
  "List subtitle tracks" -> "Any subtitle track available?";
  "Any subtitle track available?" -> "Download subs with --skip-download" [label="yes"];
  "Any subtitle track available?" -> "Stop: explain limitation" [label="no"];
  "Download subs with --skip-download" -> "Convert VTT/SRT to TXT";
  "Convert VTT/SRT to TXT" -> "Report output files";
}

Read the full file on GitHub · 142 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. 12d ago First seen · 142 lines · 38 tokens per session scan A 2e541166d03f

Subscribe to this mod's changes

youtube-transcribe-yt-dlp is a skill published in the GitHub repository supermaciz/sessions-chronicle (5 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,168 once invoked, about $0.0002 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

nsfc-budget

A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.

huangwb8/ChineseResearchLaTeX · 138 tokens

nsfc-ref-alignment

A read-only checker for references in NSFC LaTeX proposals. It compares citations with the bibliography and flags missing entries, field errors, and possible mismatches between claims and papers.

huangwb8/ChineseResearchLaTeX · 90 tokens

nature-data

Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…

Galaxy-Dawn/claude-scholar · 90 tokens

pptgen-drawio

A tool for generating multi-page Draw.io presentations and exporting them as PowerPoint files. It supports thesis-defence slides and general presentation decks, with optional PowerPoint templates.

xstongxue/best-skills · 80 tokens

publication-chart-skill

This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants…

Galaxy-Dawn/claude-scholar · 77 tokens

transfer-old-latex-to-new

A content-migration tool for moving text, references, and other written material into an existing ChineseResearchLaTeX document template. It works within the template’s allowed content files and does not change the template’s shared code or layout.

huangwb8/ChineseResearchLaTeX · 161 tokens