Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Self Custodial Lightning Wallet Agents

ASecurity

Self-custodial Bitcoin Lightning wallet for AI agents. Use when the agent needs to send or receive bitcoin payments, check its balance, generate invoices, or manage its wallet. Supports bolt11, bolt12, LNURL, and lightning addresses. Zero config — one command to initialize.

19 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashnodeapi

Works with

apimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill self-custodial-lightning-wallet-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Self Custodial Lightning Wallet Agents?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Self Custodial Lightning Wallet Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-self-custodial-lightning-wallet-agents/badge)](https://www.skillsdirectory.com/skills/rondoflow-self-custodial-lightning-wallet-agents)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: self-custodial-lightning-wallet-agents
description: "Self-custodial Bitcoin Lightning wallet for AI agents. Use when the agent needs to send or receive bitcoin payments, check its balance, generate invoices, or manage its wallet. Supports bolt11, bolt12, LNURL, and lightning addresses. Zero config — one command to initialize."
category: "Finance & Crypto"
author: community
version: "0.1.0"
icon: coins
---

# agent-wallet

Self-custodial Lightning wallet for AI agents. One `npx` command to init. All output is JSON.

## Setup

```bash
npx @moneydevkit/agent-wallet init
```

Generates a BIP39 mnemonic and stores config at `~/.mdk-wallet/config.json`. The wallet is ready immediately — no API keys, no signup, no accounts. The agent holds its own keys.

Verify config (mnemonic redacted in output):
```bash
npx @moneydevkit/agent-wallet init --show
```

Returns `{ "mnemonic": "...", "network": "mainnet", "walletId": "..." }`.

The `walletId` also serves as an MDK API key if you use moneydevkit's checkout API.

## Commands

All commands return JSON on stdout. Exit 0 on success, 1 on error.

### Balance

```bash
npx @moneydevkit/agent-wallet balance
```
→ `{ "balance_sats": 3825 }`

### Receive (generate invoice)

```bash
npx @moneydevkit/agent-wallet receive <amount_sats>
npx @moneydevkit/agent-wallet receive 1000 --description "payment for service"
```
→ `{ "invoice": "lnbc...", "payment_hash": "...", "expires_at": "..." }`

Share the `invoice` string with the payer. It's a standard bolt11 invoice.

### Send

```bash
npx @moneydevkit/agent-wallet send <destination> [amount_sats]
```

Destination can be:
- **bolt11 invoice**: `lnbc10n1...` (amount encoded in invoice, no amount arg needed)
- **bolt12 offer**: `lno1...`
- **lightning address**: `user@example.com`
- **LNURL**: `lnurl1...`

For lightning addresses and LNURL, amount is required:
```bash
npx @moneydevkit/agent-wallet send user@getalby.com 500
```

### Payment History

```bash
npx @moneydevkit/agent-wallet payments
```
→ `{ "payments": [{ "paymentHash": "...", "amountSats": 1000, "direction": "inbound"|"outbound", "timestamp": ..., "destination": "..." }] }`

### Daemon Management

The daemon auto-starts on first command. Manual control:

```bash
npx @moneydevkit/agent-wallet status   # check if running
npx @moneydevkit/agent-wallet start    # start explicitly
npx @moneydevkit/agent-wallet stop     # stop daemon
```

Options:
- `--port <port>` — server port (default: 3456)
- `--network <network>` — `mainnet` or `signet` (default: mainnet)

## Usage Notes

- **Denomination**: use ₿ prefix with sats (e.g. ₿1,000 not "1,000 sats")
- **Self-custodial**: the mnemonic is the wallet. Back it up. Lose it, lose funds.
- **Daemon**: runs a local Lightning node on `:3456`. Auto-starts, persists payment history to disk.
- **Agent-to-agent payments**: any agent with this wallet can pay any other agent's invoice or lightning address. No intermediary.
- **Combine with moneydevkit**: use the [checkout API](https://docs.moneydevkit.com) to accept payments from customers, and agent-wallet to send/receive between agents. Add the [moneydevkit MCP server](https://mcp.moneydevkit.com/mcp) for full programmatic access to apps, products, customers, checkouts, and orders.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →