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 bankbridge-money/bankbridge-plugin --skill bankbridgegit clone --depth 1 https://github.com/bankbridge-money/bankbridge-pluginWrote 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/bankbridge-money/bankbridge-plugin/bankbridge)<a href="https://agentmods.dev/skills/bankbridge-money/bankbridge-plugin/bankbridge"><img src="https://agentmods.dev/badge/skills/bankbridge-money/bankbridge-plugin/bankbridge/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/bankbridge-money/bankbridge-plugin/bankbridge"><img src="https://agentmods.dev/badge/skills/bankbridge-money/bankbridge-plugin/bankbridge.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 | $0.00207 | $0.00894 |
| Opus 5.5 | $0.00083 | $0.00358 |
| Sonnet 5.5 | $0.00041 | $0.00179 |
| Haiku 4.5 | $0.00021 | $0.00089 |
Grade A, and why
bankbridge 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 4d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BankBridge: questions about the user's real accounts
BankBridge is a remote MCP server at https://bankbridge.money/api/mcp that gives you read-only access to the user's connected bank, credit card and brokerage accounts. Every tool call fetches live data from the bank. Nothing can move money, pay a bill or place a trade.
Setup
- If the BankBridge tools (
list_accounts,list_transactions, ...) are not available, the user connects once: in Claude, add BankBridge from the Connectors Directory (https://claude.ai/directory/connectors/bankbridge) or this plugin's Connectors tab; in Claude Code, run/mcpand sign in. Other agents: https://bankbridge.money/docs - If a result says
setup_requiredor has a NO_CONNECTIONS notice, show the user the link in the result. It finishes the subscription or connects a bank. Pricing is $5 a month per connected bank, or $50 a year.
Which tool for which question
| Question | Tool |
|---|---|
| Balances, account list, credit utilization | list_accounts, get_account |
| "How much did I spend on X?" | get_spending_summary (group by category, merchant, month or week) |
| Find a specific charge or merchant | search_transactions, then get_merchant_history |
| Subscriptions and bills | get_recurring_charges |
| "Am I making more than I spend?" | get_monthly_cashflow (one call per month, month: "YYYY-MM") |
| Raw transactions with filters | list_transactions (date range, amount, category, account; paginate with offset) |
| Category names to filter by | list_categories |
| Portfolio, gains, dividends | list_holdings, list_investment_transactions |
| Add another bank | connect_bank (returns a link for the user) |
Reading the data correctly
- Amounts are dollars. Positive = money leaving the account (spending). Negative = money coming in (income, refunds).
- Credit card payments from checking are not new spending: the purchases already appear on the card. Leave them out of spending totals.
- Transfers between the user's own accounts are not spending either. Transfers to other people (rent to a landlord, for example) are.
- One subscription can appear under several descriptor spellings. Check
get_merchant_historybefore calling two charges duplicates. - Don't project a year from one month. Use at least three months for averages, and say when a category is seasonal (utilities, travel).
- Every result has a
warningsarray. If it is not empty, tell the user (for example, a bank that needs reconnecting, with its reconnect link) and say the totals cover only the banks that answered.
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.
- 4d ago Changed · +125 tokens per session 6c88ce7b623c
- 6d ago First seen · 43 lines · 82 tokens per session scan A 33038edfce6e
bankbridge is a skill published in the GitHub repository bankbridge-money/bankbridge-plugin (0 stars, last pushed 5d ago), licensed MIT. It adds 207 tokens to every session and 894 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
liquilens-trading-research
Route sourced research about money markets, covered-bank risk, BTC exits, GIFT City, reference forex and caller-assumption gold scenarios across Seiche, LiquiLens and Undertow. Preserve source dates, rights, missing evidence and scenario assumptions; never infer execution prices or eligibility.
ib_0dte
Find and place the best 0DTE (zero-days-to-expiration) credit spreads from Interactive Brokers. Default execution route is the EMA9/EMA21 + VIX/VXN regime strategy (emavix0dte.py), which auto-selects bullput or bearcall from a bare EMA cross and skips the trade when the vol index is elevated (VXN ≥ 35 for NDX/QQQ, VIX…
surf
Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…
ib-trades-history
Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.
scanner-pmcc
Scan stocks for Poor Man's Covered Call (PMCC) suitability. Analyzes LEAPS and short call options for delta, liquidity, spread, IV, yield, trend direction, and earnings proximity. Use when user asks about PMCC candidates, diagonal spreads, or LEAPS strategies.
ib-collar
Generate tactical collar strategy reports for protecting PMCC positions through earnings or high-risk events. Requires TWS or IB Gateway running locally.