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 hassancs91/claude-youtube-editor --skill packaginggit clone --depth 1 https://github.com/hassancs91/claude-youtube-editorWrote 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/hassancs91/claude-youtube-editor/packaging)<a href="https://agentmods.dev/skills/hassancs91/claude-youtube-editor/packaging"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-youtube-editor/packaging/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/hassancs91/claude-youtube-editor/packaging"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-youtube-editor/packaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.03536 |
| Opus 5 | $0.00065 | $0.01768 |
| Sonnet 5 | $0.00026 | $0.00707 |
| Haiku 4.5 | $0.00013 | $0.00354 |
Grade A, and why
youtube-packaging 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Packaging (Title + Thumbnail)
Turns a video idea into one locked title + 3 distinct thumbnail bets built for YouTube's native A/B/C thumbnail test, plus one value-forward description — then renders the three thumbnails as real images with Nano Banana Pro.
The whole skill optimizes for one number: CTR (click-through rate). It's the metric YouTube Studio reports per thumbnail, and the only one that isolates packaging from topic and algorithm.
Where these rules come from, and what to do about it
The rules below are not generic YouTube advice — they were derived from Studio CTR data across 20 long-form videos on a real ~1M-subscriber beginner/AI channel, read in CTR order. That dataset isn't shipped (it's another channel's numbers, and its absolutes wouldn't transfer). The patterns do transfer, and they're a much better prior than guessing.
But an inherited rule is a bet, not a fact — about YOUR audience. So:
- Cold start (no channel data yet). Use these rules as-is. Say so when you package: "these are uncalibrated defaults — your own CTR data will beat them." Then tell the creator to start logging CTR from video 1.
- Calibrated (~10+ long-form videos with CTR). Run
references/channel-calibration.mdfirst, then follow that file's numbers wherever it disagrees with this one. Their data wins over anything written here.
Ask which mode you're in if it isn't obvious. Never quote a target CTR the creator hasn't measured.
The core model — read this first
Views = Reach × CTR. Two different levers, driven by two different things.
- Reach (how many people YouTube serves it to) comes from the topic and from riding known discovery waves — a tool everyone's searching, a real news moment, a broad money/free promise. Packaging cannot fix a low-ceiling topic.
- CTR comes from packaging craft — concrete promise, magnet word, barrier-drop, one bold thumbnail hook. This is the only lever this skill controls.
What ships with it
2 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.
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 · 252 lines · 130 tokens per session scan A 67a2048bf8f7
youtube-packaging is a skill published in the GitHub repository hassancs91/claude-youtube-editor (302 stars, last pushed 23d ago), licensed MIT. It adds 130 tokens to every session and 3,536 once invoked, about $0.0006 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.
Other skills, from other repositories
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
acestep
AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem…
elevenlabs
Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.
ffmpeg
Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
moviepy
Python video composition with moviepy 2.x — overlaying deterministic text on AI-generated video (LTX-2, SadTalker), compositing clips, single-file build.py video projects. Use when adding labels/captions/lower-thirds to LTX-2 or SadTalker outputs, building short ad-style spots in pure Python without Remotion, or doing…
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.