youtube-transcript

youtube-transcript is a skill for Claude Code from bacchus-labs/wrangler. It costs 48 tokens per session (1,722 once invoked), scanned B, original, MIT.

A tool for downloading the written captions, also called a transcript, from a YouTube video. It can use manually provided captions, automatically generated captions, or audio transcription as a last resort.

In plain words
What is it for?
It is for getting text from YouTube videos, including transcripts, subtitles, and captions, and converting caption files into readable plain text.
Why use it?
It removes the need to copy captions by hand and provides a fallback when a video has no usable caption track.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the wrangler plugin — 25 skills, 16 commands, 13 agents shipped together

Good fit It is for getting text from YouTube videos, including transcripts, subtitles, and captions, and converting caption files into readable plain text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bacchus-labs/wrangler/youtube-transcription
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 bacchus-labs/wrangler --skill youtube-transcription
Clone the repo
git clone --depth 1 https://github.com/bacchus-labs/wrangler

Made for: Claude Code.

Or install wrangler, the plugin that ships this one along with the rest of its 25 skills, 16 commands, 13 agents.

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-transcript

README.md
[![agentmods](https://agentmods.dev/badge/skills/bacchus-labs/wrangler/youtube-transcription/github.svg)](https://agentmods.dev/skills/bacchus-labs/wrangler/youtube-transcription)
Your own site
<a href="https://agentmods.dev/skills/bacchus-labs/wrangler/youtube-transcription"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/youtube-transcription/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-transcript

Your own site · 80×15
<a href="https://agentmods.dev/skills/bacchus-labs/wrangler/youtube-transcription"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/youtube-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,722 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00048 $0.01722
Opus 5 $0.00024 $0.00861
Sonnet 5 $0.00010 $0.00344
Haiku 4.5 $0.00005 $0.00172

Measured 12d ago against content hash d7abef24a94a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

youtube-transcript scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check-ytdlp.sh, scripts/download-transcript.sh, scripts/vtt-to-text.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt update && sudo apt install -y yt-dlp
.wrangler/memory/knowledge-base/reference-prompts/skills/youtube-transcription/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Transcript Downloader

This skill helps download transcripts (subtitles/captions) from YouTube videos using yt-dlp.

When to Use This Skill

Activate this skill when the user:

  • Provides a YouTube URL and wants the transcript
  • Asks to "download transcript from YouTube"
  • Wants to "get captions" or "get subtitles" from a video
  • Asks to "transcribe a YouTube video"
  • Needs text content from a YouTube video

Available Scripts

This skill includes modular scripts in the scripts/ directory:

Script Purpose
check-ytdlp.sh Check if yt-dlp is installed, attempt installation if not
download-transcript.sh Main workflow: download subtitles with automatic fallback
whisper-transcribe.sh Last resort: download audio and transcribe with Whisper
vtt-to-text.py Convert VTT subtitle files to plain text with deduplication

Script Location

# Scripts are located at:
SKILL_DIR="$(dirname "$0")"  # When running from skill directory
# Or use absolute path from wrangler installation

Quick Start

Option 1: Use the Main Download Script

# Download transcript (tries manual subs, then auto-generated)
./scripts/download-transcript.sh "https://www.youtube.com/watch?v=VIDEO_ID"

# Specify output directory
./scripts/download-transcript.sh "https://www.youtube.com/watch?v=VIDEO_ID" ./transcripts

Option 2: Manual Step-by-Step

# 1. Check/install yt-dlp
./scripts/check-ytdlp.sh --install

# 2. Download transcript
./scripts/download-transcript.sh "YOUTUBE_URL"

# 3. If no subtitles available, use Whisper
./scripts/whisper-transcribe.sh "YOUTUBE_URL"

How It Works

Priority Order:

  1. Check if yt-dlp is installed - install if needed
  2. List available subtitles - see what's actually available
  3. Try manual subtitles first (--write-sub) - highest quality
  4. Fallback to auto-generated (--write-auto-sub) - usually available
  5. Last resort: Whisper transcription - if no subtitles exist (requires user confirmation)
  6. Confirm the download and show the user where the file is saved
  7. Automatically convert VTT to plain text with deduplication

Read the full file on GitHub · 265 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 265 lines · 48 tokens per session scan B d7abef24a94a

Subscribe to this mod's changes

youtube-transcript is a skill published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,722 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens