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 zkp2p/zkp2p-skills --skill peer-cashoutgit clone --depth 1 https://github.com/zkp2p/zkp2p-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/zkp2p/zkp2p-skills/peer-cashout)<a href="https://agentmods.dev/skills/zkp2p/zkp2p-skills/peer-cashout"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-cashout/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/zkp2p/zkp2p-skills/peer-cashout"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-cashout.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 | $0.00033 | $0.01171 |
| Opus 5 | $0.00016 | $0.00585 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
peer-cashout 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 2d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Cash cash-outs
Use this for the Peer Cash SDK cash-out lifecycle when someone holds crypto and wants fiat delivered to a specified payment account. Peer Cash turns their Base USDC into a maker deposit: a buyer sends fiat to the payee, proves the payment, and receives USDC. A cash-out can fill in pieces. An estimate is neither a bank transfer nor a settlement guarantee.
Gather the actual payout instruction
Resolve environment, amount, source chain/token, platform, currency, payee, and the authorized funding wallet. Reuse authorization already given for that exact payout; ask only for missing decisions. Never infer a recipient from an example or add a referral fee/code of your own. Keep account details in the host's private storage, out of transcripts and committed fixtures.
Use @zkp2p/[email protected] and a host-supplied wallet. Start with canonical Base USDC; routed assets add a separate funding leg. Read the checked example for exact calls and types. Install dependencies in the consuming project with its package manager; no script here executes on import.
Execute the lifecycle
- Call
cash.capabilities()for the selected environment. Check the exact platform/currency pair, amount bounds, payee format, pricing mode, and attestation requirement. The default catalog does not prove live liquidity. UPI is a staging opt-in, not a production promise. - Call
cash.estimate({ amount, currency }, { includeEta: false })before registering a payee. Report the estimate and variable fill time. Most corridors bind a rate when an intent is signaled; Alipay/CNY snapshots a creation-time rate. Use the returned corridor pricing, not one global assumption. - Register/prove the specified payee through the existing identity flow where required. New Wise, PayPal, and Alipay payees can require a browser identity attestation.
PAYEE_VERIFICATION_REQUIREDis an unmet prerequisite; do not substitute dummy proof or put session cookies in code. - For a host-controlled signer, call
cash.prepare(input). This registers payee details with the curator, although it does not broadcast. Review every returnedtxs[]with its matchingsteps[], including chain, spender, value, token amount, and target. Submit sequentially through the authorized wallet and confirm each receipt. Do not infer that every prepared plan contains exactly two transactions. - Pass the confirmed createDeposit receipt to
cash.finalizePreparedCashout(receipt). Persist the returneddepositId, transaction hash, chain/environment, and owning account before subsequent work. The Cash resume key isescrowAddress_onchainId; keep the returned string rather than rebuilding it from a bare number. - For every
accessPolicyPaymentMethodsentry, submitcash.prepareAccessPolicy(depositId, paymentMethod)from the deposit owner's wallet and confirm it. Restricted legs require this post-creation policy; creation and policy are not atomic. Do not advertise the order as fully configured while any required policy is missing. If a policy fails, resume policy setup on the existing deposit. - Poll
cash.order(depositId)or usewatchwith an abort signal and timeout. Report partial fills andnextActions. DistinguishfiatOwedfrom verifiedfiatPaid, payment ID, and released USDC. Completion is verified delivery, not the initial optimisticawaiting-buyersnapshot.
What ships with it
1 file 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.
- 2d ago First seen · 45 lines · 33 tokens per session scan A a296a150e9a5
peer-cashout is a skill published in the GitHub repository zkp2p/zkp2p-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,171 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 2026-09-10.
Other skills, from other repositories
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
marginfi
MarginFi — Solana lending and borrowing.
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…