AgentPay: Skill for Claude Code

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

agentpay-provider is a skill for Claude Code, Codex from alefnt/AgentPay. It costs 16 tokens per session (1,022 once invoked), scanned B, original, MIT.

A guide for creating a paid AI service that other agents can discover and call through AgentPay. It covers service descriptions, pricing, payment holds, task execution, settlement, and refunds after failures.

In plain words
What is it for?
Use it to publish services, set per-call prices, accept paid requests, run task handlers, deliver results, settle successful payments, and cancel failed requests.
Why use it?
It provides the payment and service workflow needed when an AI agent must charge other agents for work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

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-provider/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-provider

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alefnt/agentpay/agentpay-provider"><img src="https://agentmods.dev/badge/skills/alefnt/agentpay/agentpay-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,022 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00016 $0.01022
Opus 5.5 $0.00006 $0.00409
Sonnet 5.5 $0.00003 $0.00204
Haiku 4.5 $0.00002 $0.00102

Measured 2mo ago against content hash 882b5b9924f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agentpay-provider scanned grade B with 1 finding 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('http://registry.agentpay.dev/api/agents', { method: 'POST',
.agent/skills/agentpay-provider/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentPay Provider Skill

Use this skill when you need to create a paid service that other AI agents can discover and pay for using the AgentPay protocol.

What This Does

Creates an HTTP server that:

  1. Advertises services with pricing
  2. Creates Hold Invoices when agents request services
  3. Executes tasks after payment is locked
  4. Settles invoices after successful delivery
  5. Automatically cancels (refunds) on failure

Quick Start

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

// 1. Define your service
const provider = new ServiceProvider({
  fiberRpcUrl: 'http://127.0.0.1:8227',
  services: [{
    name: 'translate',
    description: 'Translate text to any language',
    pricing: { model: 'per-call', amount: '100000000', asset: 'USDI' }, // $0.01 USDI
    input_schema: { text: 'string', target: 'string' },
    output_schema: { translated: 'string' },
  }],
});

// 2. Register handler
provider.onTask('translate', async (input: any) => {
  // Your AI logic here
  const translated = await myTranslationModel(input.text, input.target);
  return { translated };
});

// 3. Start server
provider.listen(3000);
// �?[AgentPay Provider] Listening on 0.0.0.0:3000
// �?[AgentPay Provider] Services: translate (100000000 USDI)

Multiple Services

const provider = new ServiceProvider({
  services: [
    {
      name: 'translate',
      description: 'Translate text',
      pricing: { model: 'per-call', amount: '100000000', asset: 'USDI' },
      input_schema: { text: 'string', target: 'string' },
      output_schema: { translated: 'string' },
    },
    {
      name: 'summarize',
      description: 'Summarize long text',
      pricing: { model: 'per-call', amount: '500000000', asset: 'USDI' },
      input_schema: { text: 'string', maxLength: 'number' },
      output_schema: { summary: 'string' },
    },
  ],
});

provider.onTask('translate', async (input: any) => {
  return { translated: `[translated] ${input.text}` };
});

provider.onTask('summarize', async (input: any) => {
  return { summary: `[summary of ${input.text.length} chars]` };
});

provider.listen(3000);

Read the full file on GitHub · 145 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 · 145 lines · 16 tokens per session scan B 882b5b9924f4

Subscribe to this mod's changes

agentpay-provider is a skill published in the GitHub repository alefnt/AgentPay (0 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,022 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

agentpay-provider compared with skills from other repositories

agentpay-provider next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentpay-provideralefnt/AgentPaySkill07mo agoMITB16Claude Code, Codex
sector-rotationHKUDS/Vibe-TradingSkill38ktodayMITA39Claude Code, Codex
strategy-pivot-designertradermonty/claude-trading-skillsSkill3.7ktodayMITA28Claude Code, Codex
twitter-readerhimself65/finance-skillsSkill3.5k4d agoMITA110Claude Code
energy-procurementhashgraph-online/awesome-codex-pluginsSkill1.5ktodayApache-2.0A93Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex
multi-expert-analyzerdigoal/blogSkill8.6k4d agoGPL-2.0A292Codex