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 skills add erikrubstein/monarch-mcp2 --skill monarch-transaction-reviewgit clone --depth 1 https://github.com/erikrubstein/monarch-mcp2Wrote 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/skills/erikrubstein/monarch-mcp2/monarch-transaction-review)<a href="https://agentmods.dev/skills/erikrubstein/monarch-mcp2/monarch-transaction-review"><img src="https://agentmods.dev/badge/skills/erikrubstein/monarch-mcp2/monarch-transaction-review/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.
<a href="https://agentmods.dev/skills/erikrubstein/monarch-mcp2/monarch-transaction-review"><img src="https://agentmods.dev/badge/skills/erikrubstein/monarch-mcp2/monarch-transaction-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.01631 |
| Opus 5 | $0.00039 | $0.00816 |
| Sonnet 5 | $0.00015 | $0.00326 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
monarch-transaction-review 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 11d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monarch Transaction Review
Core Rule
Never mark a transaction reviewed during AI preparation. Only mark a transaction reviewed during the human review stage after the user explicitly says to mark it reviewed.
Use the Monarch MCP server tools. Match the tool group to the user's request:
- Transaction preparation or human review queues: use
transactions_*plustags_*. - Cashflow summaries, trends, or breakdowns: use
cashflow_*. - Report-style grouped spending/income analysis: use
reports_*. - Budgets, budget months, budget category amounts, or rollover settings: use
budget_*. - Recurring bills, subscriptions, income, or expected payment schedules: use
recurring_*. - Accounts, balances, net worth, or account history: use
accounts_*. - Receipts, receipt matching, or receipt settings: use
receipts_*. - Merchants, categories, tags, household, goals, or investments: use the matching group.
Do not list transactions merely to answer an aggregate request when a purpose-built Monarch tool exists. For example, answer "cashflow breakdown for last month" with cashflow_get_cashflow_breakdown, not transactions_list_transactions, unless the user asks to inspect the underlying transactions.
If the request is not about transaction preparation or human review, do not add workflow tags, update transaction review status, or update memory unless the user explicitly provides a reusable preference or correction.
Private Memory
Read the private memory file before reviewing transactions:
~/.config/monarch/transaction-review-memory.md
If it does not exist, create it from references/memory-template.md or run:
python scripts/init_memory.py
Do not store personal transaction memory in this skill folder or in a public repo. The memory file should capture:
- merchant cleanup preferences
- category choices
- tag rules
- note-writing style
- receipt expectations
- recurring bills, obligations, subscriptions, and normal spending rhythms
- account-specific or household context
- corrections learned from the user
- open questions the agent should ask about
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 154 lines · 77 tokens per session scan A 70a29d7f2f22
monarch-transaction-review is a skill published in the GitHub repository erikrubstein/monarch-mcp2 (1 stars, last pushed 23d ago), licensed MIT. It adds 77 tokens to every session and 1,631 once invoked, about $0.0004 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 skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.