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 martin-gomola/spotify-mcp --skill build-spotify-playlistgit clone --depth 1 https://github.com/martin-gomola/spotify-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/martin-gomola/spotify-mcp/build-spotify-playlist)<a href="https://agentmods.dev/skills/martin-gomola/spotify-mcp/build-spotify-playlist"><img src="https://agentmods.dev/badge/skills/martin-gomola/spotify-mcp/build-spotify-playlist/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/martin-gomola/spotify-mcp/build-spotify-playlist"><img src="https://agentmods.dev/badge/skills/martin-gomola/spotify-mcp/build-spotify-playlist.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 | $0.00088 | $0.00901 |
| Opus 5.5 | $0.00035 | $0.00360 |
| Sonnet 5.5 | $0.00018 | $0.00180 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
build-spotify-playlist 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a Spotify playlist
Use exact Spotify URIs and finish with an observed playlist, not an optimistic success message.
Choose the source
- For general discovery, draft a varied candidate list and resolve each candidate with
spotify_search. Reject mismatched artists, tribute recordings, karaoke, and unintended edits. - For taste-based work, call
spotify_sample_liked_songsso candidates span newest through oldest saves. Usespotify_saved_tracksonly for exact nearby pages or a complete audit. - For a deterministic rediscovery shortlist, call
spotify_taste_recommendations. State that it is local curation from top, recent, and sampled liked-song signals, not Spotify personalization. - For an existing playlist, resolve its exact ID and read every page with
spotify_playlist_items.
Build safely
- Preserve recording URIs returned by Spotify. Matching title and artist do not make two versions interchangeable.
- Shape an intentional arc for the activity; do not globally sort one scalar unless explicitly requested.
- Create public by default, matching Spotify's default, unless the user explicitly requires private. When public visibility is accepted, treat it as final: do not retry privacy updates, inspect the plugin request path, search for private-creation workarounds, or block track writes on a visibility warning. Only investigate visibility when private is an explicit requirement. Add at most 100 URIs per write.
- For playlist contents and order, treat
ambiguous,mismatch,stale, orpartialas stop states. Re-read before deciding what happened and never repeat the write automatically. Do not apply this stop rule to accepted public visibility. - Re-read the entire result and compare exact URIs and order. Return the playlist URL, track list, arc, skipped candidates, and verification state.
- After a successful final verification, when the client supports MCP Apps, call
spotify_render_resultsexactly once before the textual completion response. Render only the final playlist entity and includekind: playlist; a plain Markdown link is not a substitute when the renderer is available. If rendering itself fails, report that failure and fall back to the canonical Spotify link without retrying the renderer.
What ships with it
3 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.
- 2mo ago First seen · 64 lines · 88 tokens per session scan A e63c1910556e
build-spotify-playlist is a skill published in the GitHub repository martin-gomola/spotify-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 901 once invoked, about $0.0004 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 2026-08-31.
build-spotify-playlist compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-spotify-playlistmartin-gomola/spotify-mcp | Skill | 1 | 4d ago | MIT | A | 88 | Codex |
| spotify-mcp-doctorNovaLux12/spotify-mcp-server | Skill | 1 | yesterday | MIT | A | 44 | Claude Code, Codex |
| spotify-exhaustive-feature-sweepNovaLux12/spotify-mcp-server | Skill | 1 | yesterday | MIT | A | 34 | Claude Code, Codex |
| spotify-mcp-competitor-comparisonNovaLux12/spotify-mcp-server | Skill | 1 | yesterday | MIT | A | 37 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 2d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 480 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 32 | Claude Code, Codex |