ClawSafe Pay – Agent Skill

Community

Secure, human-approved agent payments.

AuthorNeurarock
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OpenClaw agents require a safe, auditable path to move funds across blockchains. This skill routes payment intents to ClawSafe Pay's publisher service, exposing a single entry point while the underlying steps—transaction drafting, AI safety review, Telegram-based human approval, signing, and broadcasting—happen automatically behind the scenes.

Core Features & Use Cases

  • OpenClaw agent can initiate cross-chain payments via the publisher_service API with a single API call.
  • Sepolia testnet payments are fully supported; other chains are placeholders for future activation.
  • The workflow is auditable and auditable: policy checks, dual-reviewer assurances, and a human-in-the-loop approval flow.

Quick Start

Use the agent to point to the publisher base URL with an agent API key and submit a simple payment intent to verify the end-to-end pipeline.

Dependency Matrix

Required Modules

python-dotenv

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ClawSafe Pay – Agent Skill
Download link: https://github.com/Neurarock/clawsafe_pay/archive/main.zip#clawsafe-pay-agent-skill

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.