ynab-mcp: Instructions file for Claude Code

CLAUDE.md

ynab-mcp CLAUDE.md is an instructions file for Claude Code from johannesbraeunig/ynab-mcp. It costs 1,754 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing an MCP server that connects to YNAB, a budgeting application.

In plain words
What is it for?
Use it when working on the ynab-mcp project, including its read-only budget analysis, category management, and transaction tools. Deleting a transaction requires explicit confirmation.
Why use it?
It gives the agent project-specific guidance about the codebase, commands, architecture, and safety rules for financial data changes.

Instructions file for Claude Code

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

This is johannesbraeunig/ynab-mcp's own configuration. It tells Claude Code how to work on ynab-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 ynab-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/johannesbraeunig/ynab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/johannesbraeunig/ynab-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,754 This file is loaded in full into every session.
When invoked 1,754 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 $0.01754 $0.01754
Opus 5 $0.00877 $0.00877
Sonnet 5 $0.00351 $0.00351
Haiku 4.5 $0.00175 $0.00175

Measured 9d ago against content hash 06088c856342, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ynab-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 9d 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 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 State

An MCP server for YNAB (You Need A Budget). Implements the full read-only budget analysis surface (section A: ynab_get_user, ynab_list_budgets, ynab_get_budget, ynab_get_budget_settings, ynab_list_accounts, ynab_get_account, ynab_list_categories, ynab_get_category, ynab_list_months, ynab_get_month, ynab_list_payees, ynab_get_payee, ynab_list_scheduled_transactions, ynab_list_transactions, ynab_get_spending_summary), category management writes (section B: ynab_create_category_group, ynab_update_category_group, ynab_create_category, ynab_update_category, ynab_assign_budgeted_amount), and transaction management (section C: ynab_create_transaction, ynab_create_transactions_bulk, ynab_update_transaction, ynab_delete_transaction). ynab_delete_transaction is the reference implementation of the project's destructive-tool safety pattern: it requires confirm: z.literal(true), is annotated destructiveHint: true via the DELETES constant in src/tools/helpers.ts, and echoes the deleted transaction's fields back in the result. There is no ynab_delete_category — YNAB's public API has no delete endpoint for categories and no hidden field on the create/update request bodies, so a category can't be deleted or hidden through the API at all; this was verified directly against the ynab SDK's CategoriesApi/NewCategory/ExistingCategory types rather than assumed. ynab_create_category and ynab_update_category accept goal_target/goal_target_date/goal_needs_whole_amount to set a category's savings goal (setting goal_target on a category with no goal creates one), but the API's write models don't expose goal_type/goal_cadence/goal_day — those are read-only on CategoryBase and get chosen by YNAB (default NEED, or MF for Credit Card Payment categories) rather than settable directly. Account/budget setup (section D) is also implemented, minus ynab_close_account: ynab_create_account, ynab_create_payee, ynab_update_payee. There is no way to close, update, or delete an account through the API either — AccountsApi in the ynab SDK only exposes create/get/list, no update or close endpoint — so, like categories, an account can be created but never closed via this server once made; document this to the user before calling ynab_create_account. All four tool areas (read-only analysis, category management, transaction management, account/budget setup) are implemented. withYnabErrorHandling in src/tools/helpers.ts appends retry guidance to every error message based on YnabToolError.retryable (429s and network errors say to back off and retry later; everything else says retrying won't help); ynab_list_accounts, ynab_list_categories, ynab_list_months, ynab_list_payees, ynab_list_scheduled_transactions, and ynab_list_transactions all accept an optional last_knowledge_of_server input and return server_knowledge in their result for delta sync — YnabClient's list methods return ListResult<T> ({ items, serverKnowledge }, defined in src/ynab/client.ts) rather than a bare array, specifically to carry this cursor. The one remaining thing not yet done is a manual end-to-end pass through Claude Desktop against a real budget, which needs a human with a YNAB account — not something this agent can do itself. See README.md for setup instructions.

Read the full file on GitHub · 36 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. 9d ago First seen · 36 lines · 1,754 tokens per session scan A 06088c856342

Subscribe to this mod's changes

ynab-mcp CLAUDE.md is an instructions file published in the GitHub repository johannesbraeunig/ynab-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 1,754 tokens to every session, about $0.0088 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.

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

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

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