goetta-finance-mcp: Instructions file for Claude Code

CLAUDE.md

goetta-finance-mcp CLAUDE.md is an instructions file for Claude Code from griffin-goepper/goetta-finance-mcp. It costs 7,170 tokens per session, scanned C, original, MIT.

A set of instructions for AI assistants working on the goetta-finance-mcp project, a local-first server that connects SimpleFIN financial data to Claude. It explains the project plan, working rules, code conventions, and layout.

In plain words
What is it for?
Use it when developing or reviewing this repository, especially when choosing project phases, planning changes, and protecting account and transaction information.
Why use it?
It gives the assistant project context and boundaries, including how to handle sensitive financial data and keep changes aligned with the approved plan.

Instructions file for Claude Code

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

This is griffin-goepper/goetta-finance-mcp's own configuration. It tells Claude Code how to work on goetta-finance-mcp 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 goetta-finance-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to griffin-goepper/goetta-finance-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/griffin-goepper/goetta-finance-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/griffin-goepper/goetta-finance-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.

agentmods badge for goetta-finance-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/griffin-goepper/goetta-finance-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/griffin-goepper/goetta-finance-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/griffin-goepper/goetta-finance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/griffin-goepper/goetta-finance-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.

agentmods 80×15 button for goetta-finance-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/griffin-goepper/goetta-finance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/griffin-goepper/goetta-finance-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,170 This file is loaded in full into every session.
When invoked 7,170 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.07170 $0.07170
Opus 5 $0.03585 $0.03585
Sonnet 5 $0.01434 $0.01434
Haiku 4.5 $0.00717 $0.00717

Measured 10d ago against content hash 31726c1c1aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

goetta-finance-mcp CLAUDE.md scanned grade C with 1 finding 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 10d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- **`SELECT * FROM read_csv('~/.ssh/id_rsa')`** — passes the prefix whitelist (`SELECT` is legitimate) and the read-only transaction (no DB mutation), but `enable_external_access=false` refuses the file open. Pinned by `
CLAUDE.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file guides Claude Code (and any other AI assistant) working on this repo. Read it at the start of every session along with PROJECT_PLAN.md.

What this project is

goetta-finance is a local-first MCP server that connects SimpleFIN to Claude. Read PROJECT_PLAN.md for the full vision, architecture, and phases. This file is about how to work on the code.

Operating principles

  1. PROJECT_PLAN.md is the source of truth. If the plan and the code disagree, fix the code or update the plan with the user's approval — don't silently diverge.
  2. Always be working on a specific phase. Ask which phase if it's unclear. Don't start Phase 3 work while Phase 2 has open items.
  3. One concern per PR-equivalent change. Don't bundle the collector refactor with the SQL-query tool work. Smaller commits are easier to review.
  4. Local-first is sacred. No telemetry, no auto-update checks, no network calls that aren't for SimpleFIN or loading dashboard JS from a CDN (and even that's an open question — see PROJECT_PLAN.md §13). If you're tempted to add one, stop and ask.
  5. The user's data is sensitive. Never log access URLs, full account numbers, or transaction descriptions at INFO or above. DEBUG is fine for development but should be off by default.
  6. This project is open-source — apply the stranger test at planning time. Each slice should ask: would a stranger installing this tomorrow with their own SimpleFIN credentials benefit equally, or am I building for myself? User-state (rules, categories, account flags, transaction overrides) lives in the user's DB or user-local config (prefixes.txt, config.json). Codebase state (default seeds, regex patterns the analysis code applies, displayed copy) should be minimal and broadly applicable, with extension paths documented in CUSTOMIZATION.md. Three classes of issue to watch: (a) accidental personal-data leakage — grep at code-review time; (b) me-specific defaults that should be configurable — catch at planning; (c) US-only / bank-specific assumptions baked into schema or display — catch at planning. Surfacing this before merging is cheaper than retrofitting generality later (see migration 0007 for the retrofit cost).

Read the full file on GitHub · 249 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. 10d ago First seen · 249 lines · 7,170 tokens per session scan C 31726c1c1aa3

Subscribe to this mod's changes

goetta-finance-mcp CLAUDE.md is an instructions file published in the GitHub repository griffin-goepper/goetta-finance-mcp (1 stars, last pushed 29d ago), licensed MIT. It adds 7,170 tokens to every session, about $0.0358 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens