soundcloud-mcp CLAUDE.md

soundcloud-mcp CLAUDE.md is an instructions file for coding agents from jamiew/soundcloud-mcp. It costs 1,721 tokens per session, scanned A, original, MIT.

A set of coding instructions for the soundcloud-mcp project, which connects coding tools to SoundCloud. It explains the project layout, its Node.js and Cloudflare Workers servers, and how shared code and API checks should be handled.

In plain words
What is it for?
Understanding where to edit the project, building and type-checking both servers, maintaining imports and TypeScript settings, and verifying SoundCloud playlist operations.
Why use it?
It gives coding agents the project-specific rules they need to make consistent changes and test them against the live SoundCloud API.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/jamiew/soundcloud-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/jamiew/soundcloud-mcp

Wrote 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.

agentmods badge for soundcloud-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jamiew/soundcloud-mcp/claude-md.svg)](https://agentmods.dev/instructions/jamiew/soundcloud-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jamiew/soundcloud-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jamiew/soundcloud-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,721 This file is loaded in full into every session.
When invoked 1,721 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01721 $0.01721
Opus 5 $0.00860 $0.00860
Sonnet 5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured 3d ago against content hash 9baed9bda960, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

soundcloud-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 3d 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.

CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Working notes for agents in this repo. See PLAN.md for status and the full API audit.

Layout

One package, pnpm, Node 22+. Two servers over one shared core:

  • src/client.ts, tools.ts, types.ts, server.ts, icon.tsshared. Runtime-neutral: no Node APIs, no Workers APIs. A tool change belongs here and lands in both servers at once.
  • src/index.ts + src/stdio/ — the stdio server. pnpm build first; clients run the compiled build/index.js, not the TS.
  • src/worker.ts + src/worker/ — the Cloudflare Workers server.

Two tsconfigs, because Node and Workers disagree about fetch/Request even though they share source files. pnpm typecheck runs both; tsconfig.build.json must keep excluding the worker paths, since exclude replaces rather than extends the base.

Relative imports need .js extensions everywhere — the Node build is NodeNext and requires them. Wrangler's bundler resolves them to .ts fine.

Verify stdio changes against the live API with pnpm verify, which exercises every read tool plus a create/read/delete playlist round-trip, checks the resources and templates, and cleans up after itself. For the worker, at minimum pnpm exec wrangler deploy --dry-run proves it still bundles.

SoundCloud API rules

Authoritative sources, in order: the OpenAPI spec at https://github.com/soundcloud/api (openapi/api.yaml), SoundCloud's Agents.md in that same repo, then https://developers.soundcloud.com/docs/api/guide. Check the spec before adding an endpoint — several plausible-looking ones were removed from the public API and now return 405 (see PLAN.md).

  • Two hosts. https://api.soundcloud.com for the API, https://secure.soundcloud.com for /authorize and /oauth/token. The legacy api.soundcloud.com/oauth2/token is explicitly deprecated.
  • Authorization: OAuth <token> — not Bearer. This fails silently-ish (401) if you copy a Spotify-shaped client.
  • URNs, not numeric ids. Paths take soundcloud:tracks:123. Numeric ids still resolve today but are deprecated; normalize at the client boundary.
  • Refresh tokens are single-use. Every refresh returns a new one. Persist it or the next refresh fails permanently and the user has to re-auth.
  • PKCE is mandatory (OAuth 2.1). The verifier must survive the redirect — in the worker it lives in KV keyed by the OAuth state token.
  • Client-credentials tokens are rate limited hard: 50 per 12h per app, 30 per hour per IP. Cache them; never mint one per request.
  • Pagination is cursor-based. Pass linked_partitioning=true and follow next_href, which is an absolute URL — fetch it as-is, do not re-base it onto the API root. Default page 50, max 200.
  • Playlist writes replace the whole tracklist — there is no append endpoint. Read, concatenate, PUT. Track ids above int32 (2147483647) must be sent as URN strings or the API returns 422 with no useful message.
  • access is playable | preview | blocked. Blocked tracks have no stream. /tracks/{urn}/streams returns time-limited URLs; the older /stream endpoint is deprecated.

Read the full file on GitHub · 130 lines

Changes

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.

  1. 3d ago First seen · 130 lines · 1,721 tokens per session scan A 9baed9bda960

Subscribe to this mod's changes

soundcloud-mcp CLAUDE.md is an instructions file published in the GitHub repository jamiew/soundcloud-mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0086 per session on Opus 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 2026-09-01.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens