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 agentmods add skills/alefnt/agentpay/agentpay-paymentnpx skills add alefnt/AgentPay --skill agentpay-paymentgit clone --depth 1 https://github.com/alefnt/AgentPayWhat 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 | $0.00012 | $0.00823 |
| Opus 5 | $0.00006 | $0.00411 |
| Sonnet 5 | $0.00002 | $0.00165 |
| Haiku 4.5 | $0.00001 | $0.00082 |
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 yesterday.
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 — 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:
- Provider locks funds with a Hold Invoice
- Client pays �?funds are locked (not transferred)
- Provider does the work
- Provider reveals preimage �?funds settle to provider
- 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 |
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.
- yesterday First seen · 109 lines · 12 tokens per session scan A de3021f7cd0b
agentpay-payment is a skill published in the GitHub repository alefnt/AgentPay (0 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 823 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 2026-08-31.
Other skills, from other repositories
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.
subtitle-translator
Translate subtitle files (SRT, ASS) and video/media with embedded subtitles into any target language with high linguistic quality, sliding context window, timestamp alignment, and formatting preservation. Use when the user asks to translate a subtitle file (.srt, .ass) or video subtitles.