youtube-thumbnails

youtube-thumbnails is a skill for Claude Code, Codex from nikhilbhansali/youtube-data-skills. It costs 72 tokens per session (956 once invoked), scanned A, original, MIT.

A YouTube thumbnail downloader that collects the most-viewed thumbnails from a channel’s regular videos, Shorts, and live streams, then puts them in an Obsidian index. YouTube is a video platform, and thumbnails are the preview images shown for videos.

In plain words
What is it for?
Use it to review a channel’s thumbnail designs, create a visual reference board, or gather examples for new videos.
Why use it?
It removes the need to save thumbnails one by one or compare them manually across a channel.

Skill for Claude CodeCodex

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

Good fit Use it to review a channel’s thumbnail designs, create a visual reference board, or gather examples for new videos.

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

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-thumbnails

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-thumbnails"><img src="https://agentmods.dev/badge/skills/nikhilbhansali/youtube-data-skills/youtube-thumbnails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 956 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 $0.00072 $0.00956
Opus 5 $0.00036 $0.00478
Sonnet 5 $0.00014 $0.00191
Haiku 4.5 $0.00007 $0.00096

Measured 11d ago against content hash 002898000d6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

youtube-thumbnails 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/download_thumbnails.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.

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-thumbnails/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Thumbnail Downloader

Downloads the top 10 most-viewed thumbnails per category (regular videos, Shorts, live streams) from any YouTube channel.

Usage

/youtube-thumbnails @ChannelHandle
/youtube-thumbnails @ChannelHandle --skip-verify
/youtube-thumbnails https://youtube.com/@Handle
/youtube-thumbnails UCxxxxxxx

Instructions

Step 1: Parse Arguments

  • Channel identifier (required): @handle, channel URL, or channel ID (UCxxxxxxx)
  • --skip-verify (optional): skip Level 2 HTTP verification for faster execution
  • --scan-limit N (optional): cap uploads scanned (default: whole channel)

Step 2: Get the API Key

Check the user's Claude memory for a YouTube Data API v3 key. If not found, ask:

"I need a YouTube Data API v3 key to fetch channel data. You can get one from the Google Cloud Console. Please paste your key."

Step 3: Run the Bundled Script

Run scripts/download_thumbnails.py — resolve the path relative to this skill's own directory:

YT_API_KEY=API_KEY python3 <skill-dir>/scripts/download_thumbnails.py CHANNEL_ARG [--skip-verify]

Dependencies: pip3 install google-api-python-client requests.

Step 4: Report Results

Tell the user:

  • The thumbnails folder: reports/thumbnails/<channel-slug>-<YYYY-MM-DD>/
  • Thumbnails downloaded per category (videos, shorts, live streams)
  • The path to index.md inside that folder
  • The data file: reports/data/thumbnails-<channel-slug>-<YYYY-MM-DD>.json
  • Quota consumed
  • Suggest opening index.md in Obsidian to see all thumbnails with embedded images

How Classification Works

Level 1 — API classification (from videos.list with liveStreamingDetails):

  • Live stream: has actualStartTime or scheduledStartTime
  • Short: duration between 1 and 180 seconds
  • Video: everything else

Priority is live stream > short > regular.

Level 2 — HTTP verification (skipped with --skip-verify):

  • Shorts: HEAD /shorts/{id} returns 200 for a real Short, 303 redirect otherwise
  • Live streams: the watch page says "Streamed live" for a real stream, "Premiered" for a premiere

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file 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. 11d ago First seen · 102 lines · 72 tokens per session scan A 002898000d6f

Subscribe to this mod's changes

youtube-thumbnails is a skill published in the GitHub repository nikhilbhansali/youtube-data-skills (2 stars, last pushed 24d ago), licensed MIT. It adds 72 tokens to every session and 956 once invoked, about $0.0004 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

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

html-to-video-pipeline

Reliable HTML-to-MP4 rendering via headless browser recording (Playwright/Puppeteer) + ffmpeg — the ordering, gotchas, and verification steps you MUST get right or the output silently rots. Trigger whenever the user is building or debugging any pipeline that turns an HTML/CSS/JS page (single-file, multi-composition…

XiaomiMiMo/MiMo-Code · 0 tokens

browser-video-recording

Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography, zoom-follow framing, ffprobe/thumbnail verification, and optional native recording compatibility checks. Use when the user asks to…

MengTo/Skills · 114 tokens

record-video

Record and upload a short browser interaction video artifact.

ColeMurray/background-agents · 12 tokens

playwright-recording

Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

digitalsamba/claude-code-video-toolkit · 53 tokens

demo-video

Agent-recorded product demo videos — choreograph a real browser flow with a cursor overlay and camera zooms, encode from raw frames, and package for PR evidence or social posts. Project specifics come from .demo-video.yaml.

compozy/compozy · 48 tokens