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/jamiew/spotify-mcp/claude-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/instructions/jamiew/spotify-mcp/claude-md)<a href="https://agentmods.dev/instructions/jamiew/spotify-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jamiew/spotify-mcp/claude-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 | $0.01846 | $0.01846 |
| Opus 5 | $0.00923 | $0.00923 |
| Sonnet 5 | $0.00369 | $0.00369 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
spotify-mcp CLAUDE.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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides essential guidance for working with the Spotify MCP server codebase.
Essential Commands
Development
uv run spotify-mcp- Start the MCP server (local alias; the package publishes asspotify-mcp-jamiew, so end users runuvx spotify-mcp-jamiew)uv sync- Sync dependenciesuv run pytest- Run all tests (must pass before commits)uv run mypy src/- Type checking (must pass before commits)- Optional speedup on mypy 2.x:
uv run mypy src/ --num-workers 4(parallel checking)
- Optional speedup on mypy 2.x:
Environment Setup
Required environment variables:
SPOTIFY_CLIENT_ID- Spotify API Client IDSPOTIFY_CLIENT_SECRET- Spotify API Client Secret
Three-tier configuration (highest priority first):
- Environment variables (for production/MCP usage)
.envfile (for local development)pyproject.tomldefaults (fallback - edit[tool.spotify-mcp.env]section)
Git Workflow
Quality Gates: Before any commit, ALWAYS run:
uv run mypy src/- Type checking must passuv run pytest- All tests must pass
Commit Message Format:
Brief description of change
Detailed explanation of what and why.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
Releasing
Publishing is fully automated via OIDC trusted publishing — no tokens stored anywhere.
- Bump
versioninpyproject.toml, commit, and create a GitHub release for tagvX.Y.Z(the/releaseskill orrelease.shdoes the tag +gh release create). - The
release: publishedevent triggers.github/workflows/publish.yml, which tests → builds → publishes to PyPI (pypa/gh-action-pypi-publish, OIDC) → publishes to the MCP Registry (mcp-publisher login github-oidc), injecting the tag version intoserver.jsonat publish time.
The package publishes to PyPI as spotify-mcp-jamiew and to the registry as io.github.jamiew/spotify-mcp.
One-time setup (already required before the first successful run):
- PyPI: register a trusted publisher for project
spotify-mcp-jamiew→ ownerjamiew, repospotify-mcp, workflowpublish.yml. - MCP Registry: the
io.github.jamiew/*namespace is authenticated automatically via GitHub OIDC.
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.
- 4d ago First seen · 144 lines · 1,846 tokens per session scan A c58678e6a1a9
spotify-mcp CLAUDE.md is an instructions file published in the GitHub repository jamiew/spotify-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,846 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
spotatui copilot-instructions.md
Copilot instructions for LargeModGames/spotatui, covering copilot instructions for spotatui, build & run, ci checks (run before opening a pr), run a single test and example.
WaveeMusic CLAUDE.md
Claude Code instructions for christosk92/WaveeMusic, covering claude.md, what this repository is, commands and working rules.
WaveeMusic AGENTS.md
AGENTS.md instructions for christosk92/WaveeMusic: Guidance for AI agents working in this repo. The complete rules are in CLAUDE.md (read it first); this file is the short form for agents that do not load CLAUDE.md automatically.
spotatui AGENTS.md
AGENTS.md instructions for LargeModGames/spotatui, covering agents.md, build & run, ci checks (run before opening a pr), run a single test and example.
spotatui CLAUDE.md
Claude Code instructions for LargeModGames/spotatui, covering claude.md, build & run, ci checks (run before opening a pr), run a single test and example.
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.