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/jamiew/monarch-mcp/claude-mdgit clone --depth 1 https://github.com/jamiew/monarch-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/jamiew/monarch-mcp/claude-md)<a href="https://agentmods.dev/instructions/jamiew/monarch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jamiew/monarch-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 | $0.06684 | $0.06684 |
| Opus 5 | $0.03342 | $0.03342 |
| Sonnet 5 | $0.01337 | $0.01337 |
| Haiku 4.5 | $0.00668 | $0.00668 |
Grade A, and why
monarch-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 — 446 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.
PII & Data Privacy
CRITICAL: Never commit or include personally identifiable financial data in code, docs, tests, or commit messages. This includes:
- Real account names (e.g., specific credit card names like "Main Credit Card")
- Real merchant names from the user's transaction history
- Real transaction IDs, category IDs, or account IDs from Monarch Money
- Real dollar amounts tied to specific transactions
- Any data that could identify the user's financial institutions or spending habits
Use generic, obviously-fake examples instead: "Main Credit Card", "Corner Deli", "cat_001", "txn_123". Brand names like "Starbucks" are fine as generic illustrative examples in docstrings — the distinction is between "examples of merchants" vs "data from the user's actual account."
Development Commands
Basic Operations
uv sync- Install dependencies and create/update virtual environmentuv run python server.py- Run the MCP server directly for testinguv add <package>- Add new dependencies to the projectuv remove <package>- Remove dependencies from the project
Testing & Validation
uv run pytest tests/ -v --tb=short- Run all testsuv run mypy server.py- Type checkinguv run ruff check .- Lintuv run ruff format --check .- Format check (useruff format .to auto-fix)uv run python server.py- Test server directly (all logs to stderr)MONARCH_FORCE_LOGIN=true uv run python server.py- Force fresh login (if session expires)
Debugging Startup Issues (Updated July 2025)
- Session expired: Delete
~/.monarch-mcp/session.pickleor setMONARCH_FORCE_LOGIN=true - JSON parse errors: Fixed - all stdout output suppressed with
contextlib.redirect_stdout() - MCP protocol compliance: All logging/warnings redirected to stderr, third-party lib output suppressed
- AsyncIO errors: Fixed - uses
run_stdio_async()in async context - SSL warnings: Suppressed from gql.transport.aiohttp to prevent stdout contamination
- Date serialization errors: Fixed -
build_date_filter()returns ISO strings for JSON safety - Broken pipe errors: Fixed - comprehensive graceful shutdown and error recovery implemented
- Date parsing failures: Enhanced with multi-format fallbacks and helpful error messages
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 · 446 lines · 6,684 tokens per session scan A 37c1e7a1036b
monarch-mcp CLAUDE.md is an instructions file published in the GitHub repository jamiew/monarch-mcp (20 stars, last pushed 2mo ago), licensed MIT. It adds 6,684 tokens to every session, about $0.0334 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 2026-08-30.
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.