AgentPay: Skill for Claude Code

.agent/skills/agentpay-payment/SKILL.md

agentpay-payment is a skill for Claude Code, Codex from alefnt/AgentPay. It costs 12 tokens per session (823 once invoked), scanned A, original, MIT.

A skill for paying another AI agent for a service through AgentPay on the Fiber Network, a payment network. It uses a temporary locked payment that is released when the work is completed or refunded if it times out.

In plain words
What is it for?
Paying an agent for tasks such as translation, code review, or data analysis, then calling that agent's service endpoint.
Why use it?
It provides a way to arrange payment and service delivery without sending the money immediately. The setup requires the AgentPay SDK and access to a Fiber node or managed hub.

Skill for Claude CodeCodex

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

This is alefnt/AgentPay's own configuration. It tells Claude Code and Codex how to work on AgentPay itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AgentPay configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alefnt/AgentPay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alefnt/AgentPay/main/.agent/skills/agentpay-payment/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alefnt/AgentPay

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 agentpay-payment

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alefnt/agentpay/agentpay-payment"><img src="https://agentmods.dev/badge/skills/alefnt/agentpay/agentpay-payment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 823 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 $0.00012 $0.00823
Opus 5.5 $0.00005 $0.00329
Sonnet 5.5 $0.00002 $0.00165
Haiku 4.5 $0.00001 $0.00082

Measured 2mo ago against content hash de3021f7cd0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentpay-payment 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 2mo 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.

.agent/skills/agentpay-payment/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentPay Payment Skill

Use this skill when an AI agent needs to pay another agent for a service (translation, code review, data analysis, etc.) using the AgentPay protocol.

What This Does

AgentPay uses Hold Invoice (Fiber Network PTLC) to guarantee trustless payments:

  1. Provider locks funds with a Hold Invoice
  2. Client pays �?funds are locked (not transferred)
  3. Provider does the work
  4. Provider reveals preimage �?funds settle to provider
  5. If timeout �?funds automatically refund to client

Prerequisites

  • AgentPay SDK installed: npm install @agentpay-dev/sdk
  • A running Fiber node (or Hub API key for managed mode)

How to Pay Another Agent

import { AgentWallet } from '@agentpay-dev/sdk';

// 1. Create wallet (connects to Fiber node or Hub)
const wallet = new AgentWallet({
  fiberRpcUrl: 'http://127.0.0.1:8227',  // local Fiber node
  // OR for managed mode:
  // hubUrl: 'https://hub.agentpay.dev',
  // hubApiKey: 'ak_...',
});

// 2. Pay and call a service in one step
const result = await wallet.payAndCall(
  'http://provider-agent:3000',   // Provider's HTTP endpoint
  'translate',                     // Service name
  { text: 'Hello', target: 'zh' }, // Input
  {
    maxBudget: '1000000000',       // Max 10 CKB
    asset: 'USDI',                 // Pay in stablecoin
    timeoutSeconds: 30,            // Auto-refund after 30s
  },
);

console.log(result.output);       // { translated: '你好' }
console.log(result.amount);       // Actual amount paid
console.log(result.payment_hash); // Payment proof

Payment Assets

Asset Description Use Case
USDI USD stablecoin (xUDT) Default �?stable pricing
CKB Native CKB token Channel deposits
BTC Bitcoin (via Cch/Lightning) Cross-chain payments
USDT Tether (xUDT) Alternative stablecoin

Supported Schemes

Scheme Description
hold 🔒 Lock �?work �?settle or refund (default, trustless)
exact Pay upfront (x402 compatible)
upto Lock max �?pay actual usage �?refund remainder

Read the full file on GitHub · 109 lines

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. 2mo ago First seen · 109 lines · 12 tokens per session scan A de3021f7cd0b

Subscribe to this mod's changes

agentpay-payment is a skill published in the GitHub repository alefnt/AgentPay (0 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 823 once invoked, about $0.0000 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 2026-08-31.

Related

agentpay-payment compared with skills from other repositories

agentpay-payment next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentpay-paymentalefnt/AgentPaySkill07mo agoMITA12Claude Code, Codex
bridgealsk1992/CloddsBotSkill3.1kyesterdayMITA13Claude Code, Codex
hyperliquidalsk1992/CloddsBotSkill3.1kyesterdayMITA19Claude Code, Codex
agentic-streetLeoYeAI/openclaw-master-skillsSkill2.2k2d agoMITA91Claude Code, Codex
marginfialsk1992/CloddsBotSkill3.1kyesterdayMITA11Claude Code, Codex
token-pickaeonfun/aeonSkill7892d agoMITA25Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex