spendlog CLAUDE.md

spendlog CLAUDE.md is an instructions file for coding agents from makz81/spendlog. It costs 663 tokens per session, scanned A, original, MIT.

A CLAUDE.md instruction file for Spendlog, an expense-tracking MCP server for Claude. It documents the technology stack, commands, architecture, database, and data flow.

In plain words
What is it for?
Running development and production commands, testing and type-checking the project, managing database migrations and seed data, and understanding its SQLite expense database.
Why use it?
It tells the coding agent how this finance application stores data and how to develop, test, and migrate it safely.

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/makz81/spendlog/claude-md
Clone the repo
git clone --depth 1 https://github.com/makz81/spendlog

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 spendlog CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/makz81/spendlog/claude-md.svg)](https://agentmods.dev/instructions/makz81/spendlog/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/makz81/spendlog/claude-md"><img src="https://agentmods.dev/badge/instructions/makz81/spendlog/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 663 This file is loaded in full into every session.
When invoked 663 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 $0.00663 $0.00663
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00066 $0.00066

Measured 4d ago against content hash c921ae042d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spendlog 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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spendlog

MCP server for expense tracking. Track finances directly in Claude.

Tech Stack

Layer Technology
Runtime Node.js 20+ (ESM, TypeScript strict)
MCP @modelcontextprotocol/sdk
Database TypeORM + better-sqlite3 (SQLite)
Validation Zod
Testing Vitest (382 tests)
i18n EN (default), DE

Commands

npm run dev          # MCP server with watch mode (tsx)
npm run build        # TypeScript build
npm run start        # Run built server
npm run test         # Run tests
npm run typecheck    # Type check (no emit)
npm run db:migrate   # Run database migrations
npm run db:seed      # Seed default categories
npm run db:reset     # Reset DB (delete + migrate + seed)

Architecture

User -> Claude LLM -> MCP Tool Call -> Zod Validation -> Service -> TypeORM -> SQLite

Data Flow

  • MCP tools receive params via stdio (Claude Desktop) or HTTP/SSE (cloud)
  • Zod validates all inputs
  • Services contain business logic
  • TypeORM entities map to SQLite tables in ~/.spendlog/spendlog.db

Key Directories

src/
  index.ts              # MCP server entry point
  server.ts             # Server setup & tool registration
  cli.ts                # CLI installer (npx spendlog)
  constants.ts          # App constants
  tools/                # MCP tool definitions (one file per tool group)
  entities/             # TypeORM entities (Transaction, Invoice, etc.)
  services/             # Business logic (pdf, sync, connection)
  db/                   # Database setup, migrations, seeds
  i18n/                 # Translation dictionaries
templates/
  invoice.hbs           # Handlebars template for PDF invoices
tests/
  tools/                # Integration tests per tool group
  helpers/              # Test utilities
  fixtures/             # Test data factories

Code Conventions

  • TypeScript strict -- no any without comment
  • MCP Tools: snake_case names, Zod schemas, English descriptions (localized via i18n)
  • Services: camelCase functions, throw errors (handled in tool layer)
  • Entities: PascalCase, TypeORM decorators, UUID primary keys
  • Files: kebab-case (transaction-service.ts)
  • Imports: external -> internal -> relative, no circular deps
  • ESM: import/export, not require

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 663 tokens per session scan A c921ae042d17

Subscribe to this mod's changes

spendlog CLAUDE.md is an instructions file published in the GitHub repository makz81/spendlog (1 stars, last pushed 2mo ago), licensed MIT. It adds 663 tokens to every session, about $0.0033 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.