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/sdeiley/monarch_mcp/claude-mdgit clone --depth 1 https://github.com/sdeiley/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/sdeiley/monarch_mcp/claude-md)<a href="https://agentmods.dev/instructions/sdeiley/monarch_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sdeiley/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 | $0.01581 | $0.01581 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
monarch_mcp CLAUDE.md scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **`refreshDb` is async** — no `execSync`, direct function calls. 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.
Monarch MCP Server
Standalone MCP server for Monarch Money personal finance data.
Repository Structure
src/
config.js # Data dir + DB path resolution (MONARCH_DATA_DIR env var)
db.js # SQLite read-only query layer (node:sqlite DatabaseSync)
token.js # Auth token loader (env var or ~/.monarch-token file)
fetch.js # Monarch GraphQL API transaction fetcher
import.js # JSON → SQLite importer with upsert + pending prune
refresh.js # Async orchestrator: fetch → import
api.js # Monarch GraphQL write client (mutations + live reads)
mirror.js # Post-write read-back verification + local-mirror sync (shared row mapping)
server.js # MCP server factory: 4 resources + 12 tools
bin/
stdio.js # stdio transport entry point
cli.js # CLI: init, refresh, serve
test/
*.test.js # node:test suite (149 tests)
fixtures/
monarch.db # Committed 5-row fixture DB
create-fixture-db.js # Regenerates the fixture
Tech Stack
- Node.js ESM —
"type": "module", requires Node >= 22.0.0 fornode:sqlite - MCP SDK —
@modelcontextprotocol/sdkwithzodfor tool schemas - SQLite —
node:sqliteDatabaseSync(no native dependencies) - Tests —
node:testrunner, all tests use fixture DB or mocked fetch
Running Tests
npm test # All 149 tests
node --test test/db.test.js # Single file
Key Design Decisions
- Configurable data dir:
MONARCH_DATA_DIRenv var or~/.monarchdefault. Every DB function accepts optionaldbPathoverride for testability. - Token at
~/.monarch-token: JSON file with{ "token": "..." }field.MONARCH_TOKENenv var takes priority. fetchTransactionsreturns data, not files. The caller (refresh.js) decides where to persist.refreshDbis async — noexecSync, direct function calls.- Fixture DB committed. 5 deterministic rows spanning 3 accounts, 3 category types, tags, and splits. Tests never touch real financial data.
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 · 95 lines · 1,581 tokens per session scan A ee668060fdb6
monarch_mcp CLAUDE.md is an instructions file published in the GitHub repository sdeiley/monarch_mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,581 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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.
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.
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).