What is hledger-mcp CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, working on an hledger accounting server. They describe the project, its TypeScript structure, commands, and development setup.

Building and developing the hledger MCP server, including its TypeScript code, executable output, configuration, and accounting-related tools.

They give the assistant project-specific context and commands, reducing guesswork when building or changing the code.

How iiAtlas/hledger-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to iiAtlas/hledger-mcp. 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/iiAtlas/hledger-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/iiAtlas/hledger-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/iiatlas/hledger-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/iiatlas/hledger-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/iiatlas/hledger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iiatlas/hledger-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/iiatlas/hledger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iiatlas/hledger-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 497 This file is loaded in full into every session.

When invoked 497 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.

Model	Per session	Once invoked
Fable 5.1	$0.00497	$0.00497
Opus 5.5	$0.00199	$0.00199
Sonnet 5.5	$0.00099	$0.00099
Haiku 4.5	$0.00050	$0.00050

Measured 2mo ago against content hash 0a34501a9ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hledger-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 2mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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

This is an HLedger MCP (Model Context Protocol) server implementation built with TypeScript. The project creates a bridge between HLedger accounting software and MCP-compatible applications using the Model Context Protocol SDK.

Commands

Building

npm run build - Compiles TypeScript to JavaScript and makes the output executable

Development

Node.js version: v24.7.0 (specified in .nvmrc)
Use nvm use to set correct Node version

Architecture

Core Structure

Entry Point: src/index.ts - Main server implementation
Output: build/index.js - Compiled executable with shebang
Binary: Available as hledger-mcp command after build

Key Components

MCP Server: Uses @modelcontextprotocol/sdk for Model Context Protocol implementation
Transport: StdioServerTransport for stdio-based communication
Validation: Zod library for schema validation
Configuration: Configurable via CLI flags for read/write behaviour
Write Tools: hledger_add_transaction, hledger_import, hledger_rewrite, hledger_remove_entry, hledger_replace_entry, and hledger_close all write through temporary copies with optional backups
Read Tools: new commands such as hledger_notes extend the reporting surface while reusing query + output-format helpers

Server Structure

The server is configured as:

Name: "hledger-mcp"
Version: "1.0.0"
Capabilities: tooling plus resource discovery (we call hledger files and register every reported ledger as an MCP resource before the transport connects)
Transport: Stdio-based communication

The server runs on stdio and logs startup message to stderr to avoid interfering with the MCP protocol communication on stdout.

Runtime flags

--read-only: disable the add-transaction tool (all attempts return a validation error). Default: off.
--skip-backup: skip creating .bak files when appending to an existing journal. Default: off.
Journal path remains the first non-flag argument; flags can be passed before or after it.

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 497 tokens per session scan A 0a34501a9ec2

Subscribe to this mod's changes

hledger-mcp CLAUDE.md is an instructions file published in the GitHub repository iiAtlas/hledger-mcp (65 stars, last pushed 8mo ago), licensed MIT. It adds 497 tokens to every session, about $0.0020 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 2026-08-30.

hledger mcp plaintext-accounting

hledger-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hledger-mcp CLAUDE.mdiiAtlas/hledger-mcp	Instructions file	65	8mo ago	MIT	A	497	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

hledger-mcp: Instructions file for Claude Code