peer-intents

peer-intents is a skill for Claude Code, Codex from zkp2p/zkp2p-skills. It costs 35 tokens per session (1,115 once invoked), scanned A, original, MIT.

A Peer buyer-intent integration for buying cryptocurrency with fiat money. The buyer pays a quoted maker, or seller, and receives crypto after the payment is verified.

In plain words
What is it for?
Use it for the fiat-to-crypto buyer journey, payment proofs from the buyer's trusted execution environment, and fulfillment of a specific order.
Why use it?
It provides a defined flow for quoting and fulfilling a buyer's order, including interrupted fulfillment. It keeps the buyer's amount, wallet, payment method, and receiving address tied to one order.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for the fiat-to-crypto buyer journey, payment proofs from the buyer's trusted execution environment, and fulfillment of a specific order.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zkp2p/zkp2p-skills/peer-intents
Install

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.

Any agent
npx skills add zkp2p/zkp2p-skills --skill peer-intents
Clone the repo
git clone --depth 1 https://github.com/zkp2p/zkp2p-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for peer-intents

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-intents/github.svg)](https://agentmods.dev/skills/zkp2p/zkp2p-skills/peer-intents)
Your own site
<a href="https://agentmods.dev/skills/zkp2p/zkp2p-skills/peer-intents"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-intents/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.

agentmods 80×15 button for peer-intents

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkp2p/zkp2p-skills/peer-intents"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-intents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01115
Opus 5 $0.00017 $0.00558
Sonnet 5 $0.00007 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 2d ago against content hash ac4318db92eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

peer-intents 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/payment-proof.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/peer-intents/SKILL.md · 45 lines

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 buyer intents

The buyer pays fiat to a quoted maker and receives crypto after payment verification. Use this skill for the buyer journey or its integration. Do not turn a request to cash out crypto into a buyer intent.

Establish the order

Resolve environment, buyer wallet, receiving address, payment platform/currency, and either exact fiat spend or exact token output. Reuse existing spending authorization for that bounded order. Use @zkp2p/[email protected]; construct Zkp2pClient with the host wallet, Base chain ID 8453, and the explicit runtime environment. Let the SDK choose the matching API/contracts; a website rebrand does not change API origins.

  1. Fetch a fresh client.getQuote with buyer and recipient addresses, destination chain/token, payment platforms, currency, amount, and isExactFiat. Fiat quote amounts are integer strings with 6 decimals. Token amounts use the destination token's decimals. Never calculate a binding order from an FX midpoint.
  2. For ordinary executable discovery, use mode: 'eligible'. If the user specifically wants staked chargeback-protected liquidity, use eligible_with_chargeback_staked and the actual buyer wallet. eligible_with_chargeback is discovery and may include insufficient-stake results. Whitelist and protection labels alone do not prove this buyer can signal.
  3. Inspect success, quote expiry, full fees, output, payee, escrow, orchestrator, and eligibility. If no acceptable quote exists, report that or ask about a material amount/platform change; never silently expand spending or choose a nearby amount.
  4. Prepare client.signalIntent.prepare with the selected quote's intent and conversion rate, pinning its escrow/orchestrator when provided. Simulate/submit through the host's authorized wallet. Persist the confirmed intent hash and signal transaction before opening the fiat payment step. If signaling reverts or the quote expires, refresh; do not ask the buyer to pay against an unconfirmed intent.
  5. Show the exact fiat amount, currency, recipient details, memo if required, and live intent expiry from the confirmed order. Payment is performed in the user's authenticated bank/payment app. A screenshot or “sent” message is not payment proof.

Read the full file on GitHub · 45 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 45 lines · 35 tokens per session scan A ac4318db92eb

Subscribe to this mod's changes

peer-intents is a skill published in the GitHub repository zkp2p/zkp2p-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,115 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.