cpbox-skills
AI Agent skills for cpbox services — pay-per-use search, RAG, and blockchain APIs powered by x402 protocol.
In the AI payments ecosystem
cpbox-skills is an early-stage project in the AI payments / x402 ecosystem, focused on agent, ai, skills, x402-payment. It currently has 3 GitHub stars and 0 forks, and sits alongside related tools like AIephant-AI-Agent-Gateway, npm:wispy-ai, helix, aser, swival, t2000.
cpbox-skills
AI Agent skills for cpbox services. Pay-per-use APIs powered by the x402 protocol.
Security note: This repo contains documentation only — no executable code or credentials. See SECURITY.md for trust and scanner-related details.
Available Skills
| Skill | Description |
|---|---|
| answers | AI-grounded answers via OpenAI-compatible /chat/completions payloads (streaming/blocking, citations, research mode) |
| batch-balance | Batch query EVM address balances via Multicall3 |
| images-search | Image search (up to 200 results) |
| llm-context | Extracted web content for RAG/grounding (GET + POST) |
| local-descriptions | AI-generated POI descriptions (requires POI IDs from web-search) |
| local-pois | POI details (requires POI IDs from web-search) |
| news-search | News search (GET + POST) |
| spellcheck | Spell correction (Did you mean?) |
| suggest | Query suggestions/autocomplete |
| videos-search | Video search (GET + POST) |
| web-search | Web search (GET + POST) |
Note: the agent discovery manifest is in
AGENTS.md.
Documentation
| Doc | Description |
|---|---|
| Rate Limiting & Security | Rate limits, credential protection, abuse prevention |
| SafeSearch defaults | Why news/images/videos have different defaults |
| Sandbox / Test environment | Testing without production costs |
| OpenAPI spec | Machine-readable API specification |
| Security & Trust | Scanner-friendly explanation; no hardcoded credentials |
| Contributing | How to add skills, PR/Issue templates |
Prerequisites
All skills in this repository use the x402 payment protocol. Complete the following setup once before using any skill.
1. Install x402-payment
npm install @springmint/x402-payment
2. Configure Wallet
The x402-payment SDK reads your wallet config (never stored in this repo). Supported sources:
| Priority | Method | Example |
|---|---|---|
| 1 | Environment variable | EVM_PRIVATE_KEY or TRON_PRIVATE_KEY |
| 2 | Project config file | ./x402-config.json |
| 3 | User config file | ~/.x402-config.json |
| 4 | mcporter config | ~/.mcporter/mcporter.json |
Environment variable (quickest):
# For EVM chains (BSC, Ethereum, Base, etc.)
export EVM_PRIVATE_KEY=<your_hex>
# For TRON
export TRON_PRIVATE_KEY=<your_hex>
Config file (persistent): use keys evm_private_key, tron_private_key in x402-config.json. See x402-payment docs.
For full configuration details, see the x402-payment documentation.
3. Verify
npx @springmint/x402-payment --check
# [OK] EVM Wallet: 0x1234...abcd
Usage
Tell your AI agent:
Read skills/batch-balance/SKILL.md and query ETH balances for 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
License
MIT
Similar projects
Alephant is an open-source AI Agent Gateway for routing, tracking, and controlling LLM usage across AI agents, members, and workflows, and for publishing agent capabilities as paid endpoints with x402 and MPP payment rails.
Autonomous AI agent with dual engine (Gemini + Claude), Memory Bank, sessions, skills.sh registry, cross-model delegation, 42+ integrations, and x402 agentic commerce
Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.
Aser is a lightweight, self-assembling AI Agent frame.
A small, powerful, open-source CLI coding agent that works with open models.
Agentic finance infrastructure.
More AI Agents projects
All AI Agents projects →
Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.
The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
