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 agentmods add instructions/obrien-matthew/mcp-spotify/agents-mdgit clone --depth 1 https://github.com/obrien-matthew/mcp-spotifyWrote 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/instructions/obrien-matthew/mcp-spotify/agents-md)<a href="https://agentmods.dev/instructions/obrien-matthew/mcp-spotify/agents-md"><img src="https://agentmods.dev/badge/instructions/obrien-matthew/mcp-spotify/agents-md.svg" alt="Measured on agentmods" 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 | $0.00289 | $0.00289 |
| Opus 5 | $0.00144 | $0.00144 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
mcp-spotify AGENTS.md 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 yesterday.
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.
This is a copy
88% identical to mcp-steam AGENTS.md — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
mcp-spotify
MCP server for Spotify.
Conventions
Follows the shared conventions from mcp-template (see its AGENTS.md for full rationale): data tools return real dict/list[dict] directly (never json.dumps); action/status tools may return a human-readable -> str, as may tools whose result is genuinely a single string (IDs, versions); errors are raised, never caught and returned as strings; empty results are empty containers ({}, []), not sentinel messages.
Layout
src/spotify_mcp/server.py-- MCP tool definitionssrc/spotify_mcp/client.py-- HTTP/API client wrappersrc/spotify_mcp/formatting.py-- response formatters that produce LLM-friendly dicts (nojson.dumps)src/spotify_mcp/validation.py-- input validatorssrc/spotify_mcp/auth.py-- credential loading
Workflow
uv sync # install deps
uv run pytest -q # run tests
uv run ruff check . # lint
uv run ruff format . # format
uv run pyright src/ # typecheck
lefthook install # set up git hooks (one-time)
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.
- yesterday Changed · -22 lines · -225 tokens per session 35a2d9d753b9
- 4d ago First seen · 49 lines · 514 tokens per session scan A 37fe5da1ee09
mcp-spotify AGENTS.md is an instructions file published in the GitHub repository obrien-matthew/mcp-spotify (0 stars, last pushed 4d ago), licensed MIT. It adds 289 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to mcp-steam AGENTS.md, differing in 14 lines, and is treated as a copy.
Other instructions, from other repositories
spotify-mcp-server CLAUDE.md
Claude Code instructions for NovaLux12/spotify-mcp-server, covering spotifymcp — claude code rules, spotify api reference, authorization, redirect uris and oauth scopes.
spotify-bulk-actions-mcp CLAUDE.md
Claude Code instructions for khglynn/spotify-bulk-actions-mcp, covering spotify bulk actions mcp, what this is, key features, tools (33) and api notes.
mcp-evernote AGENTS.md
AGENTS.md instructions for verygoodplugins/mcp-evernote, covering agents.md, project overview, build & development, install dependencies and development with hot-reload (tsx watch on src/index.ts).
focustodo-mcp CLAUDE.md
Instructions for gyozalab/focustodo-mcp: 本 repo 是 Focus To-Do 的 MCP server，工作區遷移後的路徑是 D:\workspaces\focustodo-mcp。 常用指令：npm run build、npm run dev、npm start。這個 server 使用逆向 API，變更前先讀 README.md 與 .env.example。 搬遷後的 MCP 設定需在 D:\coding 根目錄使用 claude mcp 指令更新；不要手改自動管理的設定檔。 服務正在使用時不要移動原路徑；發布或交付前讀…
mcp-evernote CLAUDE.md
Claude Code instructions for verygoodplugins/mcp-evernote, a project described as: MCP server for Evernote integration with note management and synchronization.
ticktick-mcp AGENTS.md
AGENTS.md instructions for partymola/ticktick-mcp, covering ticktick-mcp - agent guide, data safety rules, architecture, session token cache and failure classification and seams the test suite does not cross.