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/superinstance/plainsong-mcp/claude-mdgit clone --depth 1 https://github.com/SuperInstance/plainsong-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/superinstance/plainsong-mcp/claude-md)<a href="https://agentmods.dev/instructions/superinstance/plainsong-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/superinstance/plainsong-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 | $0.01829 | $0.01829 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
plainsong-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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server for Plainsong. It serves the compiler's own tools over the Model Context Protocol, and adds the one thing that is not in the compiler: an ensemble session, where several agents write one score at the same time and each owns a voice.
It depends on SuperInstance/plainsong and that repository does not
depend on this one. Keep it that way. Anything that belongs to the compiler —
notation, arranging, rendering, the tool implementations themselves — goes
there; what lives here is the protocol, the two transports, and the session.
This repository was extracted from plainsong rather than written fresh,
so plainsong/mcp/ still exists over there. That copy is on its way out. Until
it goes, a fix made here has to be made there too, and vice versa — which is
exactly the drift the split was meant to end, so the sooner it goes the better.
One piece of that is now finished. plainsong_mcp/features.py was 300 lines
duplicated byte for byte with plainsong/features.py, which is the drift
this rule exists to prevent, sitting in plain sight. Per-bar analysis is a fact
about music rather than about MCP, so it belongs to the compiler; it lives there
now and this module is a re-export. plainsong_mcp.features still imports and
returns the same objects — features.BarFeatures is plainsong.features.BarFeatures
— so nothing that used it had to change. Do not reintroduce an implementation
here: if the analysis needs something, it needs it in the compiler.
plainsong_mcp/localhost.py is the same job, now also finished. It holds the
loopback check the HTTP transport refuses rebound requests with. It used to be
a copy on purpose: the check was two copies of eight inline lines, both of
which got 127.evil.example and [::1] wrong in the same way, and a security
fix should not wait on a release of a different package. plainsong 1.4.0 is
the first release publishing plainsong.runtime.localhost, and the floor in
pyproject.toml is raised to it, so the module is a re-export now —
plainsong_mcp.localhost.host_is_local is plainsong.runtime.localhost.host_is_local
— the same move features.py made. tests/test_localhost.py still pins the
parsing behaviour case by case, plus one test asserting the identity directly,
so a third copy introduced anywhere in this package cannot drift the way the
first two did. Do not reintroduce an implementation here.
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.
- 2d ago First seen · 149 lines · 1,829 tokens per session scan A e3db7d6ea566
plainsong-mcp CLAUDE.md is an instructions file published in the GitHub repository SuperInstance/plainsong-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 1,829 tokens to every session, about $0.0091 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 2026-08-31.
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).
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.
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.
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.
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).
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.