What is you-need-an-advisor-mcp CLAUDE.md?

A set of Claude Code instructions for a Python budget-advisor project using YNAB, a budgeting service called You Need a Budget.

It is for running tests, linting, formatting, type checks, dependency setup, and other work in that repository.

It gives the coding agent the project's commands, coding conventions, testing process, and tool preferences.

How senivel/you-need-an-advisor-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to senivel/you-need-an-advisor-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/senivel/you-need-an-advisor-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/senivel/you-need-an-advisor-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/senivel/you-need-an-advisor-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/senivel/you-need-an-advisor-mcp/claude-md)

Your own site

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

Per session 1,271 This file is loaded in full into every session.

When invoked 1,271 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	$0.01271	$0.01271
Opus 5.5	$0.00508	$0.00508
Sonnet 5.5	$0.00254	$0.00254
Haiku 4.5	$0.00127	$0.00127

Measured 2mo ago against content hash cc7b82a15dc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

you-need-an-advisor-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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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 YNAB (You Need A Budget) -- your AI-powered budget advisor (YNAA = "You Need an Advisor"). Python 3.13+, managed with uv.

Commands

uv run pytest — run all tests (sockets disabled by default via pytest-socket)
uv run pytest tests/test_foo.py::test_bar — run a single test
uv run pytest -k "keyword" — run tests matching keyword
uv run ruff check . — lint
uv run ruff check --fix . — lint with auto-fix
uv run ruff format . — format
uv sync — install/sync dependencies

Code Style

Ruff handles both linting and formatting (not separate tools)
Nearly all ruff rules enabled (select = ["ALL"]) with specific ignores — check pyproject.toml [tool.ruff.lint] for the full ignore list
Google-style docstrings (convention = "google")
ANN (annotations) disabled project-wide — pyright strict owns type checking
Tests additionally exempt from D102, DOC201, PLR2004, PLR6301, RUF069
Pre-commit runs: ruff lint+format, prettier (JSON/YAML/MD), pyright type check, and standard hooks (large files, trailing whitespace, merge conflict, TOML/JSON validity). A local hook blocks .planning/ files from commits.

Tool Preferences

Prefer the Context7 MCP (resolve-library-id → query-docs) over web search when looking up library or framework documentation. Fall back to web search only if Context7 lacks coverage for the library in question.

Testing Conventions

pytest-mock over unittest.mock — use the mocker fixture instead of from unittest.mock import patch/MagicMock/AsyncMock. pytest-mock auto-cleans and is more pytest-idiomatic.
freezegun for wall-clock time — use @freeze_time for tests involving datetime.now(), date.today(), or time.time(). Not applicable to time.monotonic() (use mocker.patch for monotonic).
Hypothesis for property-based tests — use @given with strategies for functions with well-defined input/output contracts (converters, validators, parsers). Complements example-based tests, doesn't replace them.

Read the full file on GitHub · 95 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 · 95 lines · 1,271 tokens per session scan A cc7b82a15dc8

Subscribe to this mod's changes

you-need-an-advisor-mcp CLAUDE.md is an instructions file published in the GitHub repository senivel/you-need-an-advisor-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 1,271 tokens to every session, about $0.0051 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.

Finance and fintech mcp mcp-server model-context-protocol ynab you-need-a-budget

you-need-an-advisor-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
you-need-an-advisor-mcp CLAUDE.mdsenivel/you-need-an-advisor-mcp	Instructions file	1	7mo ago	MIT	A	1,271	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

you-need-an-advisor-mcp: Instructions file for Claude Code