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 rachittshah/spotify-llm-mcp --skill spotify-djgit clone --depth 1 https://github.com/rachittshah/spotify-llm-mcpWrote 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/rachittshah/spotify-llm-mcp/spotify-dj)<a href="https://agentmods.dev/skills/rachittshah/spotify-llm-mcp/spotify-dj"><img src="https://agentmods.dev/badge/skills/rachittshah/spotify-llm-mcp/spotify-dj/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/rachittshah/spotify-llm-mcp/spotify-dj"><img src="https://agentmods.dev/badge/skills/rachittshah/spotify-llm-mcp/spotify-dj.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 | $0.00083 | $0.00805 |
| Opus 5 | $0.00042 | $0.00402 |
| Sonnet 5 | $0.00017 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
spotify-dj 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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spotify DJ
Drive Spotify through the spotify-llm-mcp server's tools. You are the recommendation engine: Spotify removed its recommendation API, so recommendations come from your own music knowledge, resolved to real tracks by the server.
Prerequisites (tell the user if missing)
spotify_playerinstalled, authenticated once, running as an active device.- Spotify Premium (required for playback control).
- The
spotify-llm-mcpMCP server connected (tools appear asnow_playing,control,create_playlist_from_tracks, …). If they're absent:claude mcp add spotify-llm -- spotify-llm-mcp.
Tools at a glance
| Intent | Tool |
|---|---|
| What's playing | now_playing() |
| Play/pause/skip/volume/seek/shuffle/repeat | control(action, value?) |
| Play a song by description | play(query) |
| Play a playlist | play_playlist(playlist_id, shuffle?) |
| Search | search(query, limit?) |
| Devices | list_devices() / switch_device(name) |
| Read playlists | list_playlists() / get_playlist_tracks(name_or_id) |
| Taste | taste_profile() |
| Turn song names into tracks | resolve_tracks([{title, artist}]) |
| Build a playlist from your picks | create_playlist_from_tracks(name, tracks, description?, public?) |
| Extend a playlist | append_to_playlist(playlist_id, tracks) |
control actions: play, pause, play_pause, next, previous, shuffle, repeat, volume (0–100), seek (ms).
Core recsys workflow (playlist-based)
When the user says "recommend music like my " / "extend ":
get_playlist_tracks("<playlist>")— read the actual tracks.- Study them: genres, artists, era, energy, mood.
- From your knowledge, propose ~20 songs that fit the same vibe and are not already present, as
[{title, artist}, …]. Prefer specific, real tracks. create_playlist_from_tracks(name="<playlist> — extended", tracks=[…]).- Report added vs unresolved (the server tells you which it couldn't find). Offer to
play_playlist(playlist_id).
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.
- 10d ago First seen · 57 lines · 83 tokens per session scan A d884fe50ff62
spotify-dj is a skill published in the GitHub repository rachittshah/spotify-llm-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 83 tokens to every session and 805 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
audio-dispatch
Transcribe a meeting audio file with Voxtral diarization, classify each speaker's turns by intent, and produce a per-speaker action plan. Use when the user provides a meeting or call recording with multiple speakers.
video-editing
Operate Video Agent Runtime projects through structured MCP tools for transcript-first long-form-to-short-form editing, preview review, feedback diagnosis, narration, versioning, and approved export. Use for editing an existing runtime project; do not use for direct FFmpeg or manual project-JSON changes.
vidgrid
Give an AI agent eyes for video. Turn a local video file (MP4, MOV, WebM) into a numbered grid of frames plus a transcript that a vision model can read — so you can summarize a talk, find the exact moment something happens, read on-screen text or UI, or rank clips. Use whenever you need to watch, analyze, or…
photoshop-setup
Adobe Photoshop MCP setup — stage and load the adobepy UXP bridge, configure clients, and verify the full server connection.
photoshop-image
Adobe Photoshop image operations — create new documents, export, resize canvas, flatten, merge layers.
photoshop-layers
Adobe Photoshop layer operations — create, delete, reorder, duplicate, rename, set opacity/visibility, fill, blend modes.