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 AmineDjeghri/personal-os-setup --skill youtube-download-automationgit clone --depth 1 https://github.com/AmineDjeghri/personal-os-setupWrote 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/aminedjeghri/personal-os-setup/youtube-download-automation)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/youtube-download-automation"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/youtube-download-automation/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/aminedjeghri/personal-os-setup/youtube-download-automation"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/youtube-download-automation.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 | $0.00032 | $0.01827 |
| Opus 5.5 | $0.00013 | $0.00731 |
| Sonnet 5.5 | $0.00006 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
youtube-download-automation 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 17d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Download Automation (yt-dlp)
Trigger
Any task that drives yt-dlp — the YouTube → /media/music → Navidrome/beets pipeline below, playlist or single-link downloads, per-video metadata, chapter splitting, debugging the downloader script — and any change to the downloader script itself.
0. Gate — ask before you touch anything (MANDATORY)
This pipeline writes into the user's music library, and its script is a file in a repo. Nothing downloads and nothing gets edited until the user has seen the proposal and answered.
- Check for an existing import BEFORE you plan. Grep the video ID in
.archive.txtandoverrides.json, then look for the file under/media/music/YouTube/. Already imported → the reply is its verified state (library path +ffprobetags), not a metadata proposal; only propose when something is genuinely missing or wrong. The plan's status column is not an archive check. - Say what governed the run, in one line. Name this skill and what you did not do (no download / no edit / no git). The user asks "did you read the skill first?" whenever that isn't visible in the first reply to a dropped link.
- Before a download — a single link included.
--planfirst, then show the proposed metadata (artist | title | album | year | genre | folder) and ask for the go-ahead. There is no "small enough to skip the gate" case: a one-video link is exactly where a wrongfolderor a guessed artist is cheapest to prevent and most annoying to undo. - Before editing
yt_dl.py, the README or the overrides format. Say what changes, why, and what it affects, then wait. A link that exposes a gap in the pipeline ("genre: rai" when nothing can write a genre) is a proposal, not a mandate to patch the pipeline. - Before deleting state.
.archive.txtand the library folder are what decide whether a re-run downloads or no-ops — warn explicitly, then confirm. - Before git. commit / push / PR need explicit per-action approval (repo
AGENTS.md); a download run never commits. - A timed-out approval prompt is not consent. Stop; the user re-triggers it.
What ships with it
4 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.
- 17d ago Changed · +2 lines 726d17e0ff11
- 18d ago Changed · +17 lines · +15 tokens per session 30b4668681ae
- 27d ago First seen · 51 lines · 17 tokens per session scan A 4e602a981817
youtube-download-automation is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (654 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,827 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
hula-skill
HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to…
flow-launcher
Build Flow Launcher plugins with C# or Python JSON-RPC, configure plugin manifests, and integrate Everything search.
microsoft-powertoys
Configure PowerToys FancyZones, Run, Keyboard Manager, and Awake; automate settings and troubleshoot Windows utility behavior.
eartrumpet
Inspect and route per-application audio with EarTrumpet, WASAPI, and pycaw; troubleshoot audio sessions and output devices.
wsl-bash-crlf-or-tempfile
When a Windows shell (PowerShell/cmd) feeds a bash script into WSL, CRLF line endings can corrupt the first shell builtin; force LF or pipe via a temp file.
wsl-networking-mode-dns-fallback
When WSL's mirrored networking fails and falls back to "None", plus /etc/wsl.conf has generateResolvConf=false, the distro has no DNS; fix both layers.