llm-wallet

0
0
Source

Manage crypto wallets and make x402 micropayments with USDC stablecoins on Polygon

Install

mkdir -p .claude/skills/llm-wallet && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8107" && unzip -o skill.zip -d .claude/skills/llm-wallet && rm skill.zip

Installs to .claude/skills/llm-wallet

About this skill

LLM Wallet - Crypto Wallet & x402 Micropayments

Use llm-wallet commands to manage crypto wallets and make micropayments to paid APIs using USDC stablecoins on Polygon blockchain.

Default Network: Polygon Testnet (polygon-amoy) - safe for testing Facilitator: https://x402-amoy.polygon.technology

Quick Start

# Create wallet
llm-wallet create

# Check balance
llm-wallet balance

# Set spending limits (recommended)
llm-wallet set-limit --per-tx 0.10 --daily 5.00

# View transaction history
llm-wallet history

Wallet Management

Create Wallet

llm-wallet create [--label <name>]

Creates a new HD wallet with encryption. Returns wallet address.

Example:

llm-wallet create --label "agent-wallet"

Import Wallet

llm-wallet import --private-key <key> [--label <name>]

Import existing wallet from private key.

Check Balance

llm-wallet balance

Shows USDC balance and native token balance on current network.

Transaction History

llm-wallet history

View all transactions and payments made from this wallet.

Spending Limits

Set Limits

llm-wallet set-limit --per-tx <amount> --daily <amount>

Set per-transaction and daily spending caps in USDC.

Example:

llm-wallet set-limit --per-tx 0.10 --daily 5.00

Check Limits

llm-wallet get-limits

View current spending limits and daily usage.

x402 Payments

Make Payment

llm-wallet pay <url> [--method GET|POST] [--body <json>]

Make x402 micropayment to a paid API endpoint.

⚠️ IMPORTANT: Always ask user for approval before making payments!

Example:

# Ask user: "I need to make a payment to https://api.example.com/weather. Cost: $0.001 USDC. Approve?"
llm-wallet pay "https://api.example.com/weather?location=London"

Workflow:

  1. Check if payment is needed: llm-wallet check-payment <url>
  2. Show user: URL, estimated cost, current limits
  3. Wait for user approval
  4. Execute: llm-wallet pay <url>
  5. Confirm completion and show transaction ID

Check Payment (Pre-flight)

llm-wallet check-payment <url>

Checks if wallet can afford payment without executing it.

Dynamic API Registration

Register API

llm-wallet register-api <url> --name <tool_name>

Register a paid API endpoint as a reusable tool.

Example:

llm-wallet register-api "https://api.example.com/weather" --name weather_api

List Registered APIs

llm-wallet list-apis

Show all registered API tools.

Call Registered API

llm-wallet call-api <tool_name> [--params <json>]

Execute a registered API tool. Requires approval if payment needed.

Example:

# Ask user for approval first if cost > 0
llm-wallet call-api weather_api --params '{"location": "London"}'

Unregister API

llm-wallet unregister-api <tool_name>

Remove a registered API tool.

Seller Tools (Advanced)

Verify Payment

llm-wallet verify-payment --header <x-payment-header> --requirements <json>

Verify incoming payment from a buyer (seller-side).

Create Payment Requirements

llm-wallet create-requirements --price <amount> --pay-to <address> --url <resource-url>

Generate payment requirements for a protected resource.

Safety Rules

  1. Network Default: Always uses polygon-amoy (testnet) unless configured otherwise
  2. Approval Required: Always ask user before making payments
  3. Spending Limits: Check limits before payment attempts
  4. Transaction Logging: All payments are logged with timestamps
  5. Encryption: Wallets are encrypted with AES-256-GCM

Configuration

Environment Variables

  • WALLET_ENCRYPTION_KEY - Wallet encryption key (32+ chars, auto-generated if missing)
  • WALLET_NETWORK - Network selection (default: polygon-amoy | polygon)
  • FACILITATOR_URL - Custom facilitator URL (auto-configured)
  • WALLET_MAX_TX_AMOUNT - Per-transaction limit override
  • WALLET_DAILY_LIMIT - Daily limit override

Network Info

Common Workflows

First Time Setup

# 1. Create wallet
llm-wallet create --label "my-agent"

# 2. Set spending limits
llm-wallet set-limit --per-tx 0.10 --daily 5.00

# 3. Check balance (will be 0 initially)
llm-wallet balance

# 4. Fund wallet with testnet USDC
# User needs to: visit https://faucet.polygon.technology/

Making a Payment

# 1. Pre-check payment
llm-wallet check-payment "https://api.example.com/weather?location=London"

# 2. Show user: URL, cost estimate, current limits
# 3. Ask user: "Approve payment of $0.001 USDC to https://api.example.com/weather?"

# 4. If approved, execute payment
llm-wallet pay "https://api.example.com/weather?location=London"

# 5. Confirm and show transaction ID
llm-wallet history

Registering a Paid API

# 1. Register the API
llm-wallet register-api "https://api.example.com/translate" --name translate_api

# 2. List available APIs
llm-wallet list-apis

# 3. Call the API (with approval)
llm-wallet call-api translate_api --params '{"text": "hello", "to": "es"}'

# 4. View payment in history
llm-wallet history

Error Handling

  • Insufficient Balance: Show error and guide user to faucet (testnet) or funding instructions (mainnet)
  • Payment Rejected: Transaction reverted, check error message for details
  • Limit Exceeded: Show current limits and daily usage, suggest increasing limits
  • Network Timeout: Retry with exponential backoff (max 3 attempts)

References

See references/ folder for:

  • x402-protocol.md - x402 payment protocol overview
  • wallet-setup.md - Detailed wallet setup guide
  • examples.md - More usage examples

Notes

  • All amounts are in USDC (6 decimals)
  • Default network is testnet for safety
  • Testnet USDC has no real value
  • Always verify network before mainnet usage
  • Keep encryption key secure (never share or commit)

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

575388

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

802305

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

85172

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

465118

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

36494

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

12186

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

3,2102,751

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

4,2501,832

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,2221,672

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,3621,519

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,6681,282

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

2,0741,001