Borrowing it
Nothing to install: this file belongs to jamiew/spotify-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jamiew/spotify-mcp/main/.claude/skills/spotify-api-watch/SKILL.mdgit clone --depth 1 https://github.com/jamiew/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/jamiew/spotify-mcp/spotify-api-watch)<a href="https://agentmods.dev/skills/jamiew/spotify-mcp/spotify-api-watch"><img src="https://agentmods.dev/badge/skills/jamiew/spotify-mcp/spotify-api-watch/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/jamiew/spotify-mcp/spotify-api-watch"><img src="https://agentmods.dev/badge/skills/jamiew/spotify-mcp/spotify-api-watch.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 | $0.00092 | $0.01108 |
| Opus 5.5 | $0.00037 | $0.00443 |
| Sonnet 5.5 | $0.00018 | $0.00222 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
spotify-api-watch 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spotify API watch
Spotify ships breaking changes to the Web API with little notice and no RSS feed. This skill answers two questions: what did Spotify change, and does our server still work. Do both — a clean changelog does not mean nothing broke, because the regime flip described below happens silently.
1. Changelog sweep
uv run scripts/spotify_api_watch.py
Exit 1 means there are unreviewed entries. Spotify publishes no feed and no
changelog index, so this probes the predictable per-month URLs
(.../references/changes/<month>-<year>) and diffs against
scripts/spotify-api-seen.json.
For each NEW URL, fetch it and classify every item as:
- Breaks us — an endpoint spotipy calls, a field one of the Pydantic models in
src/spotify_mcp/fastmcp_server.pyrequires, or a path in the fallback layer at the bottom ofsrc/spotify_mcp/spotify_api.py. - Unlocks something — new capability worth a tool or a scope.
- Irrelevant — dashboard/quota/billing with no code impact.
Then re-run with --accept to record them as reviewed, and commit the updated JSON.
Only accept after you have actually read the entries.
2. Live conformance probe
The changelog tells you what Spotify announced; this tells you what our app actually gets. Requires the server connected as an MCP client — ask the user to reconnect if the tools are absent.
Run these and compare against the expectations:
| Call | Full/legacy regime | Restricted regime |
|---|---|---|
get_me |
returns email, country, product |
id only |
get_artist on any artist |
has followers, popularity |
both absent |
search_music with limit=20 |
can return >10 | capped at 10 |
save_tracks on one id |
succeeds via legacy /me/tracks |
succeeds via /me/library |
If the probe shows a flip to restricted, expect these to matter:
search_musicmax drops 50 → 10 (our schema still advertises 50).- Artist
followers/popularityand useremail/country/productvanish. Those fields are all optional on the Pydantic models, so they degrade rather than throw — keep them that way. - Playlist and library writes move to
/itemsand/me/library.with_fallbackinspotify_api.pyhandles this, but it caches per process, so the first call after a flip may fail before it settles. Watch for the "resolved to the legacy regime" log line to see which way it went.
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.
- 1mo ago Changed 1306bb1519f3
- 2mo ago First seen · 86 lines · 92 tokens per session scan A c555fd5fe683
spotify-api-watch is a skill published in the GitHub repository jamiew/spotify-mcp (12 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 1,108 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
spotify-api-watch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spotify-api-watchjamiew/spotify-mcp | Skill | 12 | 5d ago | MIT | A | 92 | Claude Code |
| spotify-exhaustive-feature-sweepNovaLux12/spotify-mcp-server | Skill | 1 | 2d ago | MIT | A | 34 | Claude Code, Codex |
| spotifyfurkangonel/cowrangler | Skill | 1 | 1mo ago | MIT | A | 15 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |