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/harmonicabot/harmonica-mcp/claude-mdgit clone --depth 1 https://github.com/harmonicabot/harmonica-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/harmonicabot/harmonica-mcp/claude-md)<a href="https://agentmods.dev/instructions/harmonicabot/harmonica-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/harmonicabot/harmonica-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 | $0.02754 | $0.02754 |
| Opus 5 | $0.01377 | $0.01377 |
| Sonnet 5 | $0.00551 | $0.00551 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
harmonica-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 — 155 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.
Project Overview
MCP (Model Context Protocol) server for Harmonica, enabling AI agents to create and query Harmonica sessions programmatically. Published to npm as harmonica-mcp.
Commands
npm run build # Compile TypeScript → dist/
npm run dev # Watch mode compilation
npm start # Run the MCP server (requires HARMONICA_API_KEY env var)
Vitest test suite — npm test (src/client.test.ts, src/methodSpec.test.ts, src/index.test.ts). No linter configured.
npm test runs npm run build first, because index.test.ts drives the built dist/index.js over stdio rather than importing a factory — what we publish is the binary, so the tests send the same tools/list a real client sends. That also catches bootstrap failures (bad import specifier, transport wiring) a unit test would miss.
Publishing
Published to npm (harmonica-mcp). Users install via npx -y harmonica-mcp.
npm version patch|minor|major # Bump version in package.json
npm publish # Runs prepublishOnly → build → publish
Architecture
AI Agent (Claude Code, etc.)
↕ stdio (MCP protocol)
harmonica-mcp (this project)
↕ HTTP (REST API)
Harmonica API (app.harmonica.chat/api/v1)
↕ SQL
Neon Postgres
This is a client of the Harmonica REST API (/api/v1/), which lives in harmonica-web-app/. ESM module ("type": "module" in package.json).
Source files:
src/index.ts— bootstrap only. Reads env, picks the transport, wires it. No tool definitions.src/tools.ts— the 26 tool definitions andcreateServer(client, version). Pure: no env reads, no filesystem, no transport.src/http.ts—startHttpServer().node:httpplus the SDK's web-standard handler. Loaded lazily, so a stdio run never pays for it.src/client.ts— HTTP client wrapping the Harmonica REST API. All methods throw on HTTP errors.src/methodSpec.ts— parses OFL method specs (method.md) into chain configs.
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 · 155 lines · 2,754 tokens per session scan A fe3f1af03636
harmonica-mcp CLAUDE.md is an instructions file published in the GitHub repository harmonicabot/harmonica-mcp (3 stars, last pushed 15d ago), licensed MIT. It adds 2,754 tokens to every session, about $0.0138 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.