GENesis-AGI: Skill for Claude Code

.claude/skills/youtube-fetch/SKILL.md

youtube-fetch is a skill for Claude Code from WingedGuardian/GENesis-AGI. It costs 103 tokens per session (2,060 once invoked), scanned A, original, MIT.

A tool-assisted way to retrieve information and automatic captions from YouTube videos. yt-dlp is a command-line program that downloads video metadata and subtitles.

In plain words
What is it for?
It is for fetching a video's title, uploader, description, and transcript so the content can be read or summarized.
Why use it?
YouTube pages can be difficult for ordinary web-reading tools to access, and long videos are hard to review without a transcript.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is WingedGuardian/GENesis-AGI's own configuration. It tells Claude Code how to work on GENesis-AGI 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 GENesis-AGI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WingedGuardian/GENesis-AGI. 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/WingedGuardian/GENesis-AGI/main/.claude/skills/youtube-fetch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/GENesis-AGI

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 youtube-fetch

README.md
[![agentmods](https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/youtube-fetch/github.svg)](https://agentmods.dev/skills/wingedguardian/genesis-agi/youtube-fetch)
Your own site
<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/youtube-fetch"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/youtube-fetch/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-fetch

Your own site · 80×15
<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/youtube-fetch"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/youtube-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,060 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 38
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 116
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00103 $0.02060
Opus 5 $0.00051 $0.01030
Sonnet 5 $0.00021 $0.00412
Haiku 4.5 $0.00010 $0.00206

Measured 6d ago against content hash 57c962b7b735, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

youtube-fetch 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 6d 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/skills/youtube-fetch/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

This skill retrieves YouTube video content (metadata and transcripts) using yt-dlp. WebFetch does not work reliably for YouTube (dynamic content, SSL issues). yt-dlp is the reliable alternative.

Prerequisite: yt-dlp must be installed (pip install yt-dlp).

Workflow

  1. Ensure yt-dlp is available (install if needed):

    which yt-dlp || pip install yt-dlp
    
  2. Fetch metadata for each video:

    yt-dlp --skip-download --print '%(title)s|||%(uploader)s|||%(description)s' 'VIDEO_URL'
    
  3. Fetch the auto-generated transcript. Request both English tracks and prefer en-orig:

    VID='VIDEO_ID'   # <- substitute the real 11-char video id
    mkdir -p ~/tmp/yt-transcripts
    rm -f ~/tmp/yt-transcripts/"$VID".*.vtt        # drop any earlier run's files
    yt-dlp --write-auto-sub --skip-download --sub-langs "en-orig,en" -o "$HOME/tmp/yt-transcripts/%(id)s" 'VIDEO_URL'
    ls ~/tmp/yt-transcripts/ | grep -F -- "$VID"
    

    The rm -f is load-bearing, not tidiness: that directory persists across runs and across videos, so a stale $VID.en-orig.vtt from an earlier fetch would satisfy step 4's preference check even when THIS fetch failed or returned only en — you would clean an old transcript and never see an error. grep -F -- because a video id may begin with -, which grep would otherwise read as options. YouTube may serve two English auto-caption tracks — en-orig ("English (Original)") and en ("English"). Usually they are the same resource. Observed 2026-09 on one video: the two were served with different cue segmentation, and the closing lines differed in wording ("subscribe" vs "subscription") — that wording difference is direct evidence of a different transcription. The same video served byte-identical tracks hours later. Cause unknown; requesting both and preferring en-orig costs one extra small download and is free insurance either way.

    en-orig exists only where the video's original audio is English. On a foreign-language video there is no en-orig, and en is a machine TRANSLATION with nothing in the file marking it as one. A requested track that does not exist is skipped silently — check the ls, and see step 6 if nothing was written.

Read the full file on GitHub · 163 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. 6d ago Changed · +65 lines 57c962b7b735
  2. 11d ago First seen · 98 lines · 103 tokens per session scan A b561a3443894

Subscribe to this mod's changes

youtube-fetch is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 2,060 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

search

Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation for Cloudflare-protected sites (PRL, Science, Nature, Google Scholar).

Muuuun/luxas · 0 tokens

qec-construct

Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…

Muuuun/luxas · 148 tokens

figure

Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level diagrams, phase-space trajectories…

Muuuun/luxas · 104 tokens

memory

Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.

Muuuun/luxas · 30 tokens

paper-figures

Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…

Muuuun/luxas · 79 tokens

compute-methods

Environment-verified friction sheets for field-standard computational tools (Rydberg pair interactions, QEC circuits, qLDPC decoding, code distance, atom dynamics, optics, quantum chemistry). Each sheet lists the tools the field actually uses, the first-use frictions that make agents wrongly abandon them, and one-line…

Muuuun/luxas · 113 tokens