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.
npx agentmods add instructions/koonn/ynab_mcp/claude-mdgit clone --depth 1 https://github.com/koonn/ynab_mcpWrote 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.
[](https://agentmods.dev/instructions/koonn/ynab_mcp/claude-md)<a href="https://agentmods.dev/instructions/koonn/ynab_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/koonn/ynab_mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00945 | $0.00945 |
| Opus 5 | $0.00473 | $0.00473 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 41 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
ynab_mcp is a personal, read-only MCP server for YNAB (You Need A Budget). It exposes budgets/categories/transactions and server-computed daily/weekly/monthly spending summaries as MCP tools, for use from Claude Desktop / Claude Code. No write operations exist or are planned.
Source of truth for requirements/design: docs/requirements.ja.md and docs/design.ja.md (Japanese = authoritative; the .en.md counterparts are LLM-input snapshots only, not to be edited independently).
Commands
- Install deps:
uv sync - Lint:
uv run ruff check . - Format:
uv run ruff format . - Test (all):
uv run pytest - Test (single):
uv run pytest tests/test_aggregations.py::TestCalculatePace::test_zero_monthly_budget_does_not_raise - Run server (stdio, requires
YNAB_API_TOKEN):uv run ynab-mcp - Import smoke test (no token required):
uv run python -c "from ynab_mcp.server import mcp" - List registered tools/prompts without a real token:
uv run python -c "import asyncio; from ynab_mcp.server import mcp; print(asyncio.run(mcp.list_tools()))"
Architecture
src/ynab_mcp/server.py—FastMCPinstance,lifespan(owns the singleYnabClientfor the process lifetime),main()entry point (mcp.run(), stdio transport).src/ynab_mcp/config.py— env var loading (YNAB_API_TOKENrequired;YNAB_DEFAULT_BUDGET_ID/YNAB_MCP_CACHE_TTL/YNAB_MCP_WEEK_STARToptional).load_settings()is only called fromlifespan, so importingserver/toolsnever requires a token to be set.src/ynab_mcp/client.py— async YNAB API client (httpx.AsyncClient), translates 401/429/404 into Japanese human-readableYnabApiError, routes every request throughcache.py.src/ynab_mcp/cache.py— in-process dict-based TTL cache, no persistence.src/ynab_mcp/aggregations.py— pure functions only (period range resolution, transfer exclusion, category summarization, monthly-budget pace proration). This is the only module covered bytests/test_aggregations.py.src/ynab_mcp/tools.py— the 4 MVP tools (list_budgets,get_categories,list_transactions,get_period_summary); gluesclient+aggregations, contains no aggregation logic of its own.src/ynab_mcp/prompts.py—daily_review/weekly_review/monthly_reviewprompt templates.
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.
- 5d ago First seen · 41 lines · 945 tokens per session scan A 29a51c4bfe43
ynab_mcp CLAUDE.md is an instructions file published in the GitHub repository koonn/ynab_mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 945 tokens to every session, about $0.0047 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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.