billy-mcp-server: Instructions file for Claude Code

CLAUDE.md

billy-mcp-server CLAUDE.md is an instructions file for Claude Code from markhm/billy-mcp-server. It costs 2,503 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code, describing how to build, run, test, and configure a server that connects to Billy, an accounting service. It also outlines the server's code structure and supported accounting data.

In plain words
What is it for?
Building and running the TypeScript server, starting development or watch mode, checking its Billy API connection, and working with contacts, invoices, products, payments, bills, and accounts.
Why use it?
It gives the coding agent the repository-specific commands, setup requirements, and environment details needed to work correctly without guessing.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is markhm/billy-mcp-server's own configuration. It tells Claude Code how to work on billy-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything billy-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to markhm/billy-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/markhm/billy-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/markhm/billy-mcp-server

Made for: Claude Code.

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 billy-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/markhm/billy-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/markhm/billy-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/markhm/billy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/markhm/billy-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for billy-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/markhm/billy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/markhm/billy-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,503 This file is loaded in full into every session.
When invoked 2,503 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02503 $0.02503
Opus 5.5 $0.01001 $0.01001
Sonnet 5.5 $0.00501 $0.00501
Haiku 4.5 $0.00250 $0.00250

Measured 17d ago against content hash 7ce4e71e54ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

billy-mcp-server 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 17d 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 · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 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.

Development Commands

Build and Development

  • npm run build - Compile TypeScript to JavaScript in build/ directory
  • npm run typecheck - Type-check without emitting
  • npm run dev - Run server in development mode with tsx
  • npm run watch - Run server in watch mode (auto-restart on changes)
  • npm start - Run the compiled server from build/index.js

Testing

  • npm test - Build, then run tests/**/*.test.js with node:test (no network, no token). tests/handlers.test.js calls every write tool without dryRun against a local Billy stub and fails on any non-GET; a new write tool must be added to its CALLS
  • npm run test:live - The same plus tests/live/, against the real account in .env. Every write there is a dry run, and the last test asserts nothing was written
  • UPDATE_SNAPSHOT=1 npm test - Regenerate tests/fixtures/tool-surface.json after an intentional change to a tool's name, schema, description or annotations
  • npm run test:connection - Quick credentials check against the live API
  • Tests import from build/, not src/: Node's type stripping rejects the BillyClient constructor parameter property, and the .js import specifiers only resolve after compiling. Anything a unit test needs must be exported

Environment Setup

  • Requires Node.js 26+ (engines, .node-version, mise.toml). process.loadEnvFile is used unguarded, which is safe at that floor
  • Copy .env.example to .env and set BILLY_ACCESS_TOKEN, or pass it via the MCP client's env block. loadDotEnv() reads .env from the package root only, never the cwd: MCP clients start the server in whatever project is open, and a planted .env could redirect the token via BILLY_API_BASE_URL or set BILLY_ALLOW_WRITES. Real environment variables take precedence over the file.
  • Run npm install to install dependencies

Read the full file on GitHub · 186 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. 17d ago Changed · +90 lines · +1,718 tokens per session 7ce4e71e54ba
  2. 2mo ago First seen · 96 lines · 785 tokens per session scan A 40209745a7b5

Subscribe to this mod's changes

billy-mcp-server CLAUDE.md is an instructions file published in the GitHub repository markhm/billy-mcp-server (3 stars, last pushed 17d ago), licensed MIT. It adds 2,503 tokens to every session, about $0.0100 per session on Opus 5.5. 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.

Related

billy-mcp-server CLAUDE.md compared with instructions from other repositories

billy-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
billy-mcp-server CLAUDE.mdmarkhm/billy-mcp-serverInstructions file317d agoMITA2,503Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode