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.
npx agentmods add skills/commandcodeai/agent-skills/youtube-transcriptnpx skills add CommandCodeAI/agent-skills --skill youtube-transcriptgit clone --depth 1 https://github.com/CommandCodeAI/agent-skillsWhat 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 | $0.00048 | $0.03316 |
| Opus 5 | $0.00024 | $0.01658 |
| Sonnet 5 | $0.00010 | $0.00663 |
| Haiku 4.5 | $0.00005 | $0.00332 |
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 2d 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.
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 This is a copy
100% identical to youtube-transcript — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 416 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
How It Works
Priority Order:
- Check if yt-dlp is installed - install if needed
- List available subtitles - see what's actually available
- Try manual subtitles first (
--write-sub) - highest quality - Fallback to auto-generated (
--write-auto-sub) - usually available - Last resort: Whisper transcription - if no subtitles exist (requires user confirmation)
- Confirm the download and show the user where the file is saved
- Optionally clean up the VTT format if the user wants plain text
Installation Check
IMPORTANT: Always check if yt-dlp is installed first:
which yt-dlp || command -v yt-dlp
If Not Installed
Attempt automatic installation based on the system:
macOS (Homebrew):
brew install yt-dlp
Linux (apt/Debian/Ubuntu):
sudo apt update && sudo apt install -y yt-dlp
Alternative (pip - works on all systems):
pip3 install yt-dlp
# or
python3 -m pip install yt-dlp
If installation fails: Inform the user they need to install yt-dlp manually and provide them with installation instructions from https://github.com/yt-dlp/yt-dlp#installation
Check Available Subtitles
ALWAYS do this first before attempting to download:
yt-dlp --list-subs "YOUTUBE_URL"
This shows what subtitle types are available without downloading anything. Look for:
- Manual subtitles (better quality)
- Auto-generated subtitles (usually available)
- Available languages
Download Strategy
Option 1: Manual Subtitles (Preferred)
Try this first - highest quality, human-created:
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.
- 2d ago First seen · 416 lines · 48 tokens per session scan B 7c832ec57899
youtube-transcript is a skill published in the GitHub repository CommandCodeAI/agent-skills (120 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 3,316 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 100% identical to youtube-transcript, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…