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 wcyiu/money-manager-mcp --skill finance-searchgit clone --depth 1 https://github.com/wcyiu/money-manager-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/skills/wcyiu/money-manager-mcp/finance-search)<a href="https://agentmods.dev/skills/wcyiu/money-manager-mcp/finance-search"><img src="https://agentmods.dev/badge/skills/wcyiu/money-manager-mcp/finance-search/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/wcyiu/money-manager-mcp/finance-search"><img src="https://agentmods.dev/badge/skills/wcyiu/money-manager-mcp/finance-search.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 | $0.00073 | $0.01441 |
| Opus 5 | $0.00036 | $0.00720 |
| Sonnet 5 | $0.00015 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
finance-search 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finance-search
Answer finance questions using ONLY the money-manager MCP tools (search,
summary, trends, merchants, duplicates, compare, recurring,
receipts, categories, accounts, backup_status,
receipt_text_search, receipt_text, receipt_regex). Never guess numbers
and never compute totals yourself from transaction lists.
Tool selection
- Totals / "how much" / comparisons →
summarywith the rightgroup_by(category|subcategory|account|month) and filters. NEVER sum transactions in-context from a longsearchlisting —summaryaggregates in SQL. - "Show me" / "find" / "when did I" →
searchwith text, category, account, date, kind, or amount filters. It also returnsmatchedandtotal_amountfor the full filter, beyond the listed page. - "What did I buy at X" / line items / anything about receipt contents →
receipt_text_searchfor the query (Chinese works directly), thenreceipt_texton the matched file for the full OCR text. Present line items as an itemized table. - "Which shops / how often" →
merchants(spend-ranked). "Before vs after X" →comparewith two date ranges. Subscriptions / regular payments →recurring. Garbled brand names →receipt_regexafterreceipt_text_searchmisses. - Unknown category/account names →
categories/accountsfirst, then filter with the exact names. - Multi-currency:
summaryreturnsby_currency+ a warning when filters mix currencies — report per-currency, never a mixed total. - Ambiguous or surprising results →
backup_statusto check data freshness and date coverage before answering.
Answer contract (every answer, no exceptions)
- State the exact date range, currency, and filters applied — e.g. "2024-01-01 to 2024-01-31, USD, kind=expense, category=Groceries".
- Cite source transactions for every claim: date, amount, account, and
tx_uid(a short table for the top contributors is ideal). - Note that deleted transactions are excluded (the tools filter
ZISDEL=0). - Caveat when OCR text looks unreliable, category is missing/
(none), or the newest backup predates the period asked about. - Amounts are reported as stored (
ZAMOUNT); cross-account totals involving transfers may double-count — caveat if transfers are in scope.
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.
- 10d ago First seen · 110 lines · 73 tokens per session scan A 9d1b0c3e60dd
finance-search is a skill published in the GitHub repository wcyiu/money-manager-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,441 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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.