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 yt-dlp-music-downloadsgit 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/yt-dlp-music-downloads)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/yt-dlp-music-downloads"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/yt-dlp-music-downloads/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/yt-dlp-music-downloads"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/yt-dlp-music-downloads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00020 | $0.02056 |
| Opus 5 | $0.00010 | $0.01028 |
| Sonnet 5 | $0.00004 | $0.00411 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade A, and why
yt-dlp-music-downloads 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 13d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube → Music Library (yt-dlp → Navidrome)
Trigger
User pastes a YouTube playlist or video link (often live performances) and wants it in the music library, tagged.
Environment (verified Aug 2026)
- Agent container mounts /media rw — the real music library (
/media/musicFLACs visible from inside the agent).ffmpegat/usr/bin/ffmpeg,uvat/usr/local/bin/uv. - Project:
/config/workspace/personal-os-setup/docs/home-server/music/youtube_ai_download/— scriptyt_dl.pywith a PEP 723# /// scriptheader (yt-dlp, mutagen;requires-python >=3.11; uv fetches a managed Python if needed). Run viauv run --no-project yt_dl.pyfrom that folder. Archive.archive.txtand staging.staging(outside/media/musicso beets never imports half-finished folders) live next to the script itself — overridesoverrides.json. README.md explains the pipeline. - Home: personal-os-setup
docs/home-server/music/youtube_ai_download/; the skill file is symlinked into~/.hermes/skills/media/— edit the project file, not the symlink. NOTE:skill_managerefuses symlinked skills — patch the project file with the patch tool. - Metadata decisions are 100% LLM-made: the script does NO title/description parsing — it is plumbing only. The plan output + overrides file are the entire decision layer.
- (optional, recommended) beets addon watches
/media/music(inotify, 300s debounce): adds last.fm genres + cover art and triggers Navidrome's rescan. The script embeds all tags itself, so without beets the files still reach Navidrome on its own scan schedule. If beets IS used: live bootlegs don't match MusicBrainz →quiet_fallback: asiskeeps the embedded tags;import.copy/move: no→ the download location IS the final location. - Navidrome: songs appear under Artists + "Live at …" albums (tag-driven; folders invisible). Offer the one-time smart playlist
Album contains "Live"— it collects every live download automatically.Other-folder clips have albumOther(excluded).
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.
- 13d ago First seen · 73 lines · 20 tokens per session scan A 1d068be595e8
yt-dlp-music-downloads is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (602 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,056 once invoked, about $0.0001 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
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…
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.
flow-launcher
Build Flow Launcher plugins with C# or Python JSON-RPC, configure plugin manifests, and integrate Everything search.
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.