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-syncgit 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-sync)<a href="https://agentmods.dev/skills/wcyiu/money-manager-mcp/finance-sync"><img src="https://agentmods.dev/badge/skills/wcyiu/money-manager-mcp/finance-sync/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-sync"><img src="https://agentmods.dev/badge/skills/wcyiu/money-manager-mcp/finance-sync.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 | $0.00048 | $0.00733 |
| Opus 5 | $0.00024 | $0.00367 |
| Sonnet 5 | $0.00010 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
finance-sync 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finance-sync
Ingestion status and reindexing for the money-manager MCP server. The server
picks up the newest .mmbak in the drop folder automatically — there is
nothing to "import"; this skill checks freshness and refreshes the OCR index.
Status check
Call backup_status and report:
- backup filename, size, active transaction count, date range, main currency
- Freshness warning: if the newest data date (or the filename's embedded
date, e.g.
20240115_093000.mmbak) is older than ~10 days, tell the user to export a fresh backup in Money Manager and upload it to the drop folder.
Receipt reindex
After the user drops new receipt photos (or asks to reindex):
- Call
reindex_receipts(addforce=trueonly if the user explicitly asks for a full rebuild — a normal run hash-skips unchanged images and is cheap). - Report the counts:
seen,skipped,ocr_ok,ocr_failed,indexed_total. - If
ocr_failed> 0, say how many and suggest re-running; repeated failures on the same files are worth listing.
Incremental runs are near-instant; a large batch of new images takes roughly 1–3 s per image on CPU.
Full / first-time index build
A full build (thousands of images, an hour or more) is too long for one tool call, but you can still run it:
- If you have shell access: run the CLI as a background job and report
the final stats when it finishes:
money-manager ocr-index(env:MONEY_PHOTOS,MONEY_INDEX). Safe to interrupt — re-running resumes via hash-skip. - MCP-only: loop
reindex_receipts(limit=50)— each call OCRs at most 50 new images (~1–2 min) then returns stats. Keep looping whileocr_ok + ocr_failed > 0, reporting cumulative progress againstseen; when a call comes back all-skipped, the build is complete.
Index ownership
Every machine owns and writes its OWN index; indexes are disposable replicas, never a shared writable file.
- Primary machine (authoritative): builds and reindexes locally
(outside any sync folder), then copies a snapshot into the synced
folder (
Money Manager/receipt_index.db) for other machines to seed from. - Other machines / agent hosts: seed a local writable index once
from the synced snapshot, then run incremental
reindex_receiptslocally. The photo source is read-only; seeded indexes diverging from the primary's is fine — every index rebuilds from source at any time. - Never point
MONEY_INDEXat a live sync folder or network share during a build: sync clients upload half-written databases and can create conflict copies.
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.
- 9d ago First seen · 70 lines · 48 tokens per session scan A 63e9b3a0b8a9
finance-sync is a skill published in the GitHub repository wcyiu/money-manager-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 733 once invoked, about $0.0002 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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.