x402engine

Pay-per-call API gateway skill — calls 63 APIs (LLMs, image/video gen, flights, hotels, crypto, web search) via x402 micropayments. Each call costs $0.001-$0.60 in USDC/USDm, enforced by a local policy engine with spend caps.

3,891 stars

Best use case

x402engine is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Pay-per-call API gateway skill — calls 63 APIs (LLMs, image/video gen, flights, hotels, crypto, web search) via x402 micropayments. Each call costs $0.001-$0.60 in USDC/USDm, enforced by a local policy engine with spend caps.

Teams using x402engine should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/x402engine/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agentc22/x402engine/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/x402engine/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How x402engine Compares

Feature / Agentx402engineStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Pay-per-call API gateway skill — calls 63 APIs (LLMs, image/video gen, flights, hotels, crypto, web search) via x402 micropayments. Each call costs $0.001-$0.60 in USDC/USDm, enforced by a local policy engine with spend caps.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# x402engine

Call 63 paid APIs via x402 micropayments. Each API call costs between $0.001 and $0.60, paid with USDC on Base/Solana or USDm on MegaETH.

## What this skill does

This skill signs and submits stablecoin micropayments to call remote APIs on the user's behalf. It uses the EVM_PRIVATE_KEY environment variable to sign on-chain payment transactions. Each call deducts a small amount from the wallet.

**Cost transparency:** When presenting results, include the cost of the call (e.g. "Bitcoin is $97,500 (cost: $0.001)"). If the user asks about spending, show full budget breakdown.

## Triggers
- "what's the price of bitcoin"
- "ethereum price"
- "show me trending crypto"
- "generate an image of a sunset"
- "run this python code"
- "transcribe this audio"
- "wallet activity of vitalik.eth"
- "ask gpt to explain x402"
- "scrape this url"
- "pin this to ipfs"
- "resolve vitalik.eth"
- "flights from JFK to LAX"
- "search hotels in Paris"
- "find cheap flights to Tokyo"
- "how much budget is left"
- "list available services"

## How it works
1. Fetch cached service catalog from discovery endpoint (default: https://x402engine.app/.well-known/x402.json).
2. Score query against 63 service descriptions to find best match.
3. Run policy preflight — check per-tx caps, daily caps, and recipient allowlist before signing.
4. Call service via @x402/fetch — handles 402 payment flow automatically.
5. Return structured data to the agent for natural-language presentation.

## Rules
- Present results naturally. Include the cost of each call so the user knows what was spent.
- If a payment fails due to insufficient funds, tell the user: "I need funds to access this service. Add USDC to your wallet to continue."
- If no matching service is found, say so plainly — don't expose internal routing details.
- Policy limits are authoritative — do not bypass spend caps or recipient allowlists.
- Keep all decisions explainable with reason codes internally.

## Security

### Required credential
- **EVM_PRIVATE_KEY** (required) — signs payment transactions. Use a dedicated wallet with limited funds — never your primary wallet. If not set, an ephemeral key is generated (no real funds, no payments possible).

### Optional configuration
These environment variables are NOT required. They provide additional controls:
- **EVM_PRIVATE_KEY_FILE** — alternative to EVM_PRIVATE_KEY; reads the key from a file instead of an env var. Use one or the other, not both.
- **X402_POLICY_PATH** — path to a JSON policy file. Defines per-transaction caps, daily spending limits, and a recipient allowlist. Without this, no spending limits are enforced beyond the wallet's on-chain balance. When configured, the engine is fail-closed: if the file is missing or invalid, all payments are denied.
- **X402_STATE_PATH** — path to a JSON file tracking daily spend and rate-limit state. Defaults to `.x402engine-state.json`.
- **X402_DISCOVERY_URL** — override the service catalog URL (default: `https://x402engine.app/.well-known/x402.json`). Use a self-hosted catalog if you don't trust the default.
- **X402_AUTOPREFLIGHT** — set to `false` to skip policy preflight checks. Enabled by default.
- **X402_DISCOVERY_REFRESH_MS** — cache TTL for the service catalog in milliseconds.

### How payments work
All payments go to the `payTo` address declared in the service catalog. The catalog is fetched from the discovery URL above. If you want to restrict which addresses can receive payments, configure a policy file with a recipient allowlist.

## Budget check
When the user asks "how much budget is left" or similar:
- Load policy and state files.
- Show daily cap remaining per chain/asset if caps are enabled.
- Show rate limit status.
- Show wallet balance.

## Dependencies
This skill requires Node.js and the following npm packages (declared in package.json):
- `@x402/fetch` — x402 payment-aware fetch wrapper
- `@x402/evm` — EVM payment scheme (Permit2 signatures)
- `viem` — Ethereum client library

Install with: `cd skills/x402engine && npm install`

## Reason Codes
- `POLICY_MISSING`, `POLICY_INVALID`
- `CHAIN_DENIED`, `ASSET_DENIED`, `RECIPIENT_DENIED`
- `PER_TX_EXCEEDED`, `DAILY_CAP_EXCEEDED`, `RATE_LIMITED`
- `ACTION_DENIED`
- `SERVICE_NOT_FOUND`
- `WALLET_UNDERFUNDED`

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation