agentmods.dev

tweazy CLAUDE.md

tweazy CLAUDE.md is an instructions file for Claude Code from aaronjmars/tweazy. It costs 813 tokens per session, scanned A, original, MIT.

Project instructions for Tweazy, a Next.js application that charges 0.01 USDC per AI query using Web3 payments. They describe development commands, the application structure, wallet handling, and payment flow.

In plain words
What is it for?
Running, building, and linting Tweazy; initializing its configuration; and changing its AI payment, wallet, network, and API systems.
Why use it?
They help an agent work within the project's existing architecture instead of guessing how its servers, payments, wallets, and configuration fit together.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 46 2d ago A scan 813 tokens original MIT
View the source file aaronjmars/tweazy tweazy.wtf
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/aaronjmars/tweazy/claude-md
Clone the repo
git clone --depth 1 https://github.com/aaronjmars/tweazy

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tweazy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaronjmars/tweazy/claude-md.svg)](https://agentmods.dev/instructions/aaronjmars/tweazy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aaronjmars/tweazy/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronjmars/tweazy/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 813 This file is loaded in full into every session.
When invoked 813 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00813 $0.00813
Opus 5 $0.00407 $0.00407
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured 6d ago against content hash 3f30c20c13ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tweazy CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

  • npm run dev - Start development server at localhost:3000
  • npm run build - Build production application
  • npm run start - Start production server
  • npm run lint - Run ESLint for code linting
  • npm run init - Initialize Tambo configuration

Project Architecture

Tweazy is a Next.js application that demonstrates pay-per-use AI with Web3 payments using x402 protocol, MCP (Model Context Protocol), and CDP Smart Wallets. Users pay 0.01 USDC per AI query.

Core Systems

Payment System (src/lib/payment.ts):

  • Universal payment handling for both Smart Wallets (CDP) and external wallets
  • Paymaster integration for gas sponsorship on Smart Wallets
  • USDC transfers on Base network (testnet/mainnet)

Wallet Architecture:

  • Smart Wallets (src/lib/smart-wallet.ts, src/lib/cdp-wallet.ts): CDP-based passkey authentication with gas sponsorship
  • External wallets: wagmi integration for MetaMask, Coinbase Wallet, etc.
  • Dual-wallet context in src/components/WalletProvider.tsx

Network Configuration (src/lib/config.ts):

  • Environment-based testnet/mainnet switching via NEXT_PUBLIC_NETWORK_MODE
  • Base Sepolia (testnet, default) and Base Mainnet support
  • Network-specific USDC contracts and RPC endpoints
  • Centralized config with secrets in environment variables only

AI Integration:

  • Tambo AI framework for generative UI with React component registry
  • MCP protocol support for extensible AI functionality
  • Every AI query is payment-gated in EnhancedMessageInput, which opens the payment flow before the request is sent
  • Dynamic component rendering based on AI responses

API Routes Structure

  • POST /api/cdp/create-wallet - Create CDP Smart Wallet
  • POST /api/cdp/balance - Check USDC balance
  • POST /api/cdp/transfer - Not implemented; returns 501 (503 when CDP is unconfigured). Mock transfers are available only behind TWEAZY_ALLOW_MOCK_PAYMENT=1.
  • POST /api/cdp/fund-wallet - Fund wallet with testnet tokens
  • POST /api/paymaster - Handle paymaster gas sponsorship

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 82 lines · 813 tokens per session scan A 3f30c20c13ce

Subscribe to this mod's changes

tweazy CLAUDE.md is an instructions file published in the GitHub repository aaronjmars/tweazy (46 stars, last pushed 2d ago), licensed MIT. It adds 813 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Web3 and blockchaincdpcoinbasemcppasskeyssmartwalletx402
Related

Other instructions, from other repositories

onchainai copilot-instructions.md

Copilot instructions for Coinyak/onchainai, covering copilot instructions — onchainai, project, 3-command ui workflow, build / test (server features required) and rules (see agents.md for full list).

Coinyak/onchainai · 969 tokens

knowmint CLAUDE.md

Instructions for Sou0327/knowmint, covering claude.md, project info, project overview, commands and architecture.

Sou0327/knowmint · 1,623 tokens

aixyz CLAUDE.md

Claude Code instructions for AgentlyHQ/aixyz, a project described as: Next.js-like framework building AI Agents that are payment-native. Bootstrap your agent with A2A, MCP, x402 payments, and ERC-8004 identity.

AgentlyHQ/aixyz · 3 tokens

cryptopilot-mcp CLAUDE.md

Claude Code instructions for cryptopilot-tools/cryptopilot-mcp, covering claude.md, project, stack, architecture and mcp tools (5).

cryptopilot-tools/cryptopilot-mcp · 1,640 tokens

onchainai CLAUDE.md

Claude Code instructions for Coinyak/onchainai, a project described as: Crypto tool directory: discover, normalize, and expose MCP, CLI, SDK, API, x402, RWA, and AI-agent tools.

Coinyak/onchainai · 5 tokens

ampersend-sdk CLAUDE.md

Instructions for edgeandnode/ampersend-sdk, covering claude.md, project overview, development commands, python setup and install python 3.13.

edgeandnode/ampersend-sdk · 1,633 tokens