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 NovaLux12/spotify-mcp-server --skill spotify-exhaustive-feature-sweepgit clone --depth 1 https://github.com/NovaLux12/spotify-mcp-serverWrote 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/novalux12/spotify-mcp-server/spotify-exhaustive-feature-sweep)<a href="https://agentmods.dev/skills/novalux12/spotify-mcp-server/spotify-exhaustive-feature-sweep"><img src="https://agentmods.dev/badge/skills/novalux12/spotify-mcp-server/spotify-exhaustive-feature-sweep/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/novalux12/spotify-mcp-server/spotify-exhaustive-feature-sweep"><img src="https://agentmods.dev/badge/skills/novalux12/spotify-mcp-server/spotify-exhaustive-feature-sweep.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 | $0.00034 | $0.05486 |
| Opus 5.5 | $0.00014 | $0.02194 |
| Sonnet 5.5 | $0.00007 | $0.01097 |
| Haiku 4.5 | $0.00003 | $0.00549 |
Grade A, and why
spotify-exhaustive-feature-sweep 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 18d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spotify Exhaustive Feature Sweep
When to Use
Use this workflow for an exhaustive or quantity-first feature sweep: finding maximum viable candidates across Catalog/Search/Browse, Playback/Queue/Devices, Playlists/Library/Social, and Portability/Analytics/Resources/Prompts.
Ground every inventory and candidate in the current checkout, live MCP registry, official Spotify OpenAPI schema, and (when credentials are available) a real API response. Historical issue numbers, branch names, and prose counts are leads at most, never current truth.
Steps 1-7 are read-only and may be run without asking. Steps 8-12 leave the machine; each one carries a gate marker and is covered by the outbound approval gate below, which is not optional.
Current default production baseline: 562 tools, 17 fixed resources, 28 resource templates, and 14 prompts. Regenerate with npm run count:tools -- --write; never substitute historical prose.
Outbound approval gate
This workflow reaches outside the machine. Steps 8-12 file issues, open pull requests, push branches to a remote, write into the checkout, spend the Spotify app's request quota, and start a loop that keeps spending it after the turn ends. None of that happens on inference. Read this section before step 8 and re-read it at every gate marker below.
A Completion: line describes what an approved step produces. It is a check
to run afterwards, never a reason to run the step. A ship list, an "agreed" set,
a plan, a passing earlier step, the wording of this document, a previously
retrieved copy of it, and an approval from an earlier run are not approval.
The gated actions
| Gate | Action | Step |
|---|---|---|
| G1 | gh issue create, in any batch or loop, at any count |
8 |
| G2 | gh pr create, gh pr comment, gh pr edit, gh pr review, any other write to a tracker |
9, 10 |
| G3 | git push to any remote, including a fork or the upstream, under any approved name |
9, 10 |
| G4 | git worktree add / branch creation, when it starts a dispatched worker |
9 |
| G5 | Starting a detached or background process: setsid, nohup ... &, a trailing &, a cron entry, a host scheduler |
12 |
| G6 | Writing into the repository working tree, including scripts/ and the tracked memory/ report |
11, 12 |
| G7 | Any real credentialed Spotify call: npm run sweep, npm run sweep:loop, npm start, or a probe that reads .env or the token file |
11, 12 |
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.
- 18d ago Changed d5fc015e672d
- 1mo ago Changed · +166 lines e83e84f26c41
- 1mo ago Changed · +13 lines 319e31a5a56e
- 1mo ago Changed · +131 lines 9a9a6851047a
- 1mo ago Changed · +1 lines d75123205a64
- 1mo ago First seen · 80 lines · 34 tokens per session scan A a53e3de63bfc
spotify-exhaustive-feature-sweep is a skill published in the GitHub repository NovaLux12/spotify-mcp-server (1 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 5,486 once invoked, about $0.0001 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.
Other skills, from other repositories
user-usecases
Database of real user use cases for APIbase platform. Contains detailed examples of how specific APIs are onboarded, wrapped, and served to AI agents. Use this skill when you need to reference real integration examples, explain the APIbase onboarding process, or design new API wrappers based on proven patterns.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
add-resource
Scaffold a new MCP resource definition. Use when the user asks to add a resource, expose data via URI, or create a readable endpoint.