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 singularityhacker/bank-skills --skill bank-skillgit clone --depth 1 https://github.com/singularityhacker/bank-skillsWrote 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/singularityhacker/bank-skills/bank-skill)<a href="https://agentmods.dev/skills/singularityhacker/bank-skills/bank-skill"><img src="https://agentmods.dev/badge/skills/singularityhacker/bank-skills/bank-skill/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/singularityhacker/bank-skills/bank-skill"><img src="https://agentmods.dev/badge/skills/singularityhacker/bank-skills/bank-skill.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 | $0.00016 | $0.02542 |
| Opus 5 | $0.00008 | $0.01271 |
| Sonnet 5 | $0.00003 | $0.00508 |
| Haiku 4.5 | $0.00002 | $0.00254 |
Grade A, and why
bank-skill 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bank Skill
Purpose
Gives AI agents traditional banking capabilities (via Wise API) and on-chain token operations (via Uniswap on Base). Agents can check balances, send money, retrieve account details, create Ethereum wallets, swap tokens, and send tokens—all through a single skill.
Prerequisites
For Banking (Wise API):
WISE_API_TOKENenvironment variable (required)- Optional:
WISE_PROFILE_ID(defaults to first available profile)
For Token Operations (Base Network):
- Optional:
CLAWBANK_WALLET_PASSWORD(wallet keystore password, defaults to "clawbank-default") - Optional:
BASE_RPC_URL(Base RPC endpoint, defaults to https://mainnet.base.org)
Operations
Banking Operations (Wise API)
1. Check Balance
Purpose: Query Wise multi-currency balances for the configured profile.
Inputs:
action:"balance"(required)currency: Currency code filter, e.g."USD"(optional — returns all if omitted)
Outputs:
- JSON array of balance objects, each with
currency,amount, andreservedAmount
Usage:
echo '{"action": "balance"}' | ./run.sh
echo '{"action": "balance", "currency": "USD"}' | ./run.sh
Example output:
{
"success": true,
"balances": [
{"currency": "USD", "amount": 1250.00, "reservedAmount": 0.00},
{"currency": "EUR", "amount": 500.75, "reservedAmount": 10.00}
]
}
2. Get Receive Details
Purpose: Retrieve account number, routing number, IBAN, and related info so others can send you payments.
Inputs:
action:"receive-details"(required)currency: Currency code, e.g."USD"(optional — returns all if omitted)
Outputs:
- JSON object with account holder name, account number, routing number (or IBAN/SWIFT for non-USD), and bank name
Usage:
echo '{"action": "receive-details"}' | ./run.sh
echo '{"action": "receive-details", "currency": "USD"}' | ./run.sh
Example output:
{
"success": true,
"details": [
{
"currency": "USD",
"accountHolder": "Your Business Name",
"accountNumber": "1234567890",
"routingNumber": "026073150",
"bankName": "Community Federal Savings Bank"
}
]
}
What ships with it
45 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.
- bankskills/__init__.py 270 B runs code
- bankskills/cli/__init__.py 164 B runs code
- bankskills/cli/app.py 1.3 KB runs code
- bankskills/cli/bank/__init__.py 31 B runs code
- bankskills/cli/bank/main.py 6.8 KB runs code
- bankskills/core/__init__.py 218 B runs code
- bankskills/core/bank/__init__.py 54 B runs code
- bankskills/core/bank/account_details.py 3.3 KB runs code
- bankskills/core/bank/activity.py 2.2 KB runs code
- bankskills/core/bank/balance_convert.py 5.5 KB runs code
- bankskills/core/bank/balances.py 1.8 KB runs code
- bankskills/core/bank/client.py 1.3 KB runs code
- bankskills/core/bank/credentials.py 1.2 KB runs code
- bankskills/core/bank/currencies.py 941 B runs code
- bankskills/core/bank/handler.py 4.5 KB runs code
- bankskills/core/bank/profiles.py 983 B runs code
- bankskills/core/bank/quotes.py 2.5 KB runs code
- bankskills/core/bank/rates.py 1.3 KB runs code
- bankskills/core/bank/recipients.py 6.7 KB runs code
- bankskills/core/bank/statements.py 3.3 KB runs code
- bankskills/core/bank/transfer.py 12 KB runs code
- bankskills/core/bank/transfers.py 4.4 KB runs code
- bankskills/core/base.py 1.2 KB runs code
- bankskills/mcp/__init__.py 203 B runs code
- bankskills/mcp/server.py 31 KB runs code
- bankskills/publishing/__init__.py 178 B runs code
- bankskills/publishing/builder.py 4.5 KB runs code
- bankskills/runtime/__init__.py 160 B runs code
- bankskills/runtime/registry.py 3.1 KB runs code
- bankskills/runtime/runner.py 3.2 KB runs code
- bankskills/sweeper.py 20 KB runs code
- bankskills/wallet.py 3.7 KB runs code
- bankskills/web/__init__.py 206 B runs code
- bankskills/web/app.py 380 B runs code
- CHANGELOG.md 1.4 KB
- examples/balance-input.json 47 B
- examples/balance-output.json 134 B
- examples/receive-details-input.json 55 B
- examples/receive-details-output.json 248 B
- examples/send-input.json 398 B
- examples/send-output.json 204 B
- pyproject.toml 296 B
- run.sh 229 B runs code
- skill.json 163 B
- uv.lock 276 KB
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 · 318 lines · 16 tokens per session scan A 319d980ff156
bank-skill is a skill published in the GitHub repository singularityhacker/bank-skills (34 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 2,542 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
bridge
Cross-chain token transfers using Wormhole and CCTP.