mdk-agent-walletSelf-custodial Bitcoin Lightning wallet for AI agents. Use when the agent needs to send or receive bitcoin payments, check its balance, generate invoices, or...
Install via ClawdBot CLI:
clawdbot install satbot-mdk/mdk-agent-walletGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://docs.moneydevkit.com/agent-walletAI Analysis
The skill manages a self-custodial Bitcoin wallet with a locally stored BIP39 mnemonic, which controls real funds on mainnet. While the daemon binds to localhost and the source is inspectable, the core risk is financial loss if the mnemonic is compromised via file system access or if the external Lightning infrastructure is malicious. The skill's stated purpose aligns with its external API usage, but the high-stakes nature of private key handling elevates the risk.
Audited Apr 18, 2026 · audit v1.0
Generated Mar 22, 2026
AI agents can use the wallet to receive micropayments for providing digital content, such as articles, code snippets, or media. For example, a content-generating agent could embed a Lightning invoice for access, enabling instant, low-fee transactions without intermediaries. This supports pay-per-use models directly within AI workflows.
AI agents can offer services like data analysis, translation, or API calls on-demand, charging per request via the wallet. Users pay by sending to a Lightning address or scanning a BOLT11 invoice generated by the agent. This enables autonomous, trustless interactions in decentralized applications (dApps) or marketplaces.
AI agents embedded in IoT devices, such as smart appliances or sensors, can use the wallet to handle microtransactions for services like energy trading or data sharing. For instance, a sensor could automatically invoice for environmental data using BOLT12 offers, facilitating machine-to-machine payments over Lightning.
AI agents can manage payments for freelance work, automatically invoicing clients via Lightning addresses and tracking balances. This reduces administrative overhead by handling invoicing, receipt, and payment history locally, ideal for platforms where agents perform tasks like writing or design on a per-project basis.
AI tutoring or training agents can charge for personalized lessons or course materials using the wallet. Students pay via invoices generated for each session, with the agent checking balances to confirm payments before delivering content. This supports scalable, low-cost education models with instant settlement.
Charge users per interaction, such as API call or content generation, using Lightning invoices. Revenue is generated from microtransactions, with low fees enabling high-volume, small-value payments. This model suits agents offering on-demand utilities like translation or data processing.
Use BOLT12 offers to create reusable payment links for subscription-based services, where users pay variable amounts periodically. This supports flexible pricing, such as tiered plans, with the agent managing recurring payments through the wallet's persistent daemon.
Integrate the wallet into AI-powered marketplaces to handle escrow-like payments between buyers and sellers, taking a commission on transactions. The agent can generate invoices for services and split payments, with revenue from percentage-based fees on each trade.
💬 Integration Tip
Start by initializing the wallet with 'npx @moneydevkit/agent-wallet init' and test with small amounts; ensure secure backup of the BIP39 mnemonic stored in ~/.mdk-wallet/config.json to prevent fund loss.
Scored Apr 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...