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 skills add nikhilbhansali/youtube-data-skills --skill youtube-thumbnailsgit clone --depth 1 https://github.com/nikhilbhansali/youtube-data-skillsWrote 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.
[](https://agentmods.dev/skills/nikhilbhansali/youtube-data-skills/youtube-thumbnails)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.mdinside that folder - The data file:
reports/data/thumbnails-<channel-slug>-<YYYY-MM-DD>.json - Quota consumed
- Suggest opening
index.mdin Obsidian to see all thumbnails with embedded images
How Classification Works
Level 1 — API classification (from videos.list with liveStreamingDetails):
- Live stream: has
actualStartTimeorscheduledStartTime - 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
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.
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.
- 11d ago First seen · 102 lines · 72 tokens per session scan A 002898000d6f
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.
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…
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…
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…
record-video
Record and upload a short browser interaction video artifact.
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.
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.