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 julianobarbosa/claude-code-skills --skill yt-musicgit clone --depth 1 https://github.com/julianobarbosa/claude-code-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/julianobarbosa/claude-code-skills/yt-music)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/yt-music"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/yt-music/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/julianobarbosa/claude-code-skills/yt-music"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/yt-music.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 | $0.00080 | $0.02738 |
| Opus 5 | $0.00040 | $0.01369 |
| Sonnet 5 | $0.00016 | $0.00548 |
| Haiku 4.5 | $0.00008 | $0.00274 |
Grade A, and why
yt-music 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 8d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Music Skill
Run bundled scripts from the skill root:
scripts/helper.py: search, library, playlists, lyrics, ratings, accountscripts/player.py: playback client and daemon managementscripts/player_daemon.py: persistent Playwright browser daemon- Runtime state is local to
./.yt-music/ - Playback uses a dedicated Playwright-managed browser profile in
./.yt-music/playwright-profile
Workflow Routing
For multi-step or composed flows, route the user into a workflow file instead of orchestrating ad-hoc:
| User intent | Workflow file |
|---|---|
| First-time setup, expired auth, daemon not running | Workflows/Setup.md |
| "Play X / play something like Y / find me music" | Workflows/PlayDiscover.md |
| "Make a playlist of …", "save the charts", artist deep cut | Workflows/BuildPlaylist.md |
| Auth errors, daemon timeouts, silent playback, cookie issues | Workflows/DiagnoseAuth.md |
| "Run the tests", verify scripts after edits, CI smoke check | Workflows/RunTests.md |
Single-shot requests (one search, one rating, one playlist get) stay inline — no workflow needed.
Decision flow
- If the user gives names instead of IDs, search first.
- For auth-required actions, run
auth checkfirst. - If auth is missing, switch into auth-guidance mode and do not continue yet.
- Only after auth succeeds, execute the original command.
- Format JSON into short tables or lists.
ID Resolution
Use search to resolve videoId, browseId, or playlistId:
uv run --with yt-musicapi python scripts/helper.py search "<query>" --type songs --limit 5
uv run --with yt-musicapi python scripts/helper.py search "<query>" --type artists --limit 3
uv run --with yt-musicapi python scripts/helper.py search "<query>" --type albums --limit 3
If results are ambiguous, ask the user which one they want.
Auth
Check auth before library, playlist, rate, subscribe, home, history, taste, upload, or auth account:
What ships with it
22 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.
- .gitignore 65 B
- pytest.ini 325 B
- README.md 2.8 KB
- references/commands.md 3.7 KB
- scripts/helper.py 25 KB runs code
- scripts/player_daemon.py 19 KB runs code
- scripts/player.py 7.5 KB runs code
- tests/__init__.py 0 B runs code
- tests/conftest.py 4.7 KB runs code
- tests/test_helper_auth.py 13 KB runs code
- tests/test_helper_library.py 3.9 KB runs code
- tests/test_helper_misc.py 13 KB runs code
- tests/test_helper_parser.py 1.7 KB runs code
- tests/test_helper_playlist.py 7.0 KB runs code
- tests/test_helper_search.py 2.1 KB runs code
- tests/test_player_client.py 18 KB runs code
- tests/test_player_daemon_pure.py 6.9 KB runs code
- Workflows/BuildPlaylist.md 3.5 KB
- Workflows/DiagnoseAuth.md 3.8 KB
- Workflows/PlayDiscover.md 3.8 KB
- Workflows/RunTests.md 4.8 KB
- Workflows/Setup.md 3.4 KB
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.
- 8d ago First seen · 236 lines · 80 tokens per session scan A 06eca282ceb1
yt-music is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 2,738 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.