A demonstration skill designed for AI agents to practice detecting, settling, and retrying Cashu-gated HTTP 402 payment flows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawtar
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install clawtar using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Clawtar?
Clawtar is a specialized demonstration tool designed for AI agents to practice the end-to-end lifecycle of Cashu HTTP 402 payment flows. By providing a controlled environment with a cryptic fortune-telling endpoint, it allows agents within the Openclaw Skills ecosystem to safely exercise the full logic of detecting a payment challenge, requesting human permission, and settling the transaction using the NUT-24 protocol.
This skill is vital for developers building autonomous agents that need to handle micropayments and paywalls. It bridges the gap between static code and dynamic, value-exchange interactions in the decentralized finance space, ensuring agents can manage financial transactions reliably without manual intervention once permission is granted.
Clawtar Use Cases
- Practicing autonomous payment handling for HTTP 402 Required responses.
- Testing the integration of cocod wallet tools within agent workflows.
- Validating NUT-24 challenge parsing and NUT-18 payment request settlement.
- Developing human-in-the-loop permission prompts for financial transactions.
- Simulating real-world Cashu-gated API interactions in a safe sandbox.
How Clawtar Works
- The agent sends a POST request to the Clawtar endpoint with a question and desired style.
- The server responds with an HTTP 402 status code and an x-cashu header containing a NUT-24 challenge.
- The agent identifies the challenge and, if available, uses cocod to handle the payment request after obtaining user permission.
- Alternatively, the agent requests a valid Cashu token directly from the user if automated tools are not available.
- Once the token is obtained, the agent retries the initial POST request, including the token in the X-Cashu header.
- The server validates the payment and returns a JSON response containing the fortune and a success status.
Clawtar Setup
To use Clawtar as part of your Openclaw Skills development, ensure you have access to a Cashu wallet or the cocod utility. No complex installation is required for the skill itself, but you should configure your agent to interact with the following endpoint:
# Example of how an agent might settle a challenge using cocod
cocod x-cashu handle "<x-cashu-challenge-string>"
Ensure your agent is pointed to https://clawtar.cashutools.dev/v1/clawtar/ask and uses the Minibits Mint for token generation.
Clawtar Data Schema & Taxonomy
The skill utilizes simple JSON objects for input and output, structured as follows:
| Field | Type | Description |
|---|---|---|
question |
String | The query sent to the service. |
style |
String | Optional: funny, chaotic, or wholesome. |
ok |
Boolean | Success indicator in the final response. |
quoted_sats |
Integer | The cost of the request (standardized at 42 sats). |
x-cashu |
Header | The NUT-24 challenge string returned on 402 status. |
X-Cashu |
Header | The final payment token sent on retry. |
Clawtar Advanced Features
- Full NUT-24 challenge support for programmatic settlement.
- Multi-style response generation (funny, chaotic, wholesome) to test agent parameter handling.
- Support for the Minibits Mint for real-world token testing and validation.
- Seamless integration path for cocod for fully automated payment workflows within Openclaw Skills.
- Built-in safety hooks requiring human permission before any autonomous fund spending.
SKILL.md
Loading
Related Openclaw Skills
Cashu Emoji
A specialized tool for embedding and extracting Cashu tokens or hidden messages within standard emojis using Unicode variation selectors.
agent-self-care
A specialized maintenance skill that automates health monitoring, process cleanup, and performance optimization for autonomous agents.
Zoho Mail CLI
A robust command-line interface for Zoho Mail that outputs machine-readable JSON for seamless automation and agent workflows.
pm-sim
A high-fidelity simulation and paper trading environment for Polymarket prediction markets featuring 26 specialized MCP tools.
SafePaste
SafePaste is a local security and compatibility layer that analyzes third-party prompts and configurations before they are applied to your OpenClaw environment.
WeChat Pack
WeChat Pack is a specialized utility for converting Markdown or Word documents into perfectly formatted HTML and organized assets for WeChat Official Accounts.
METADATA
Featured*
