A Web3 toolkit for Claude Code covering blockchain research, wallet portfolios, token and contract risk, smart-contract development, decentralized trading, DeFi, perpetual markets, bridging, and prediction-market data.

Use it to research tokens, inspect wallets and contracts, generate or audit Solidity, prepare trades and DeFi actions, analyse on-chain data, or plan cross-chain transfers.

It brings many blockchain analysis and transaction-preparation tasks into one coding-agent toolkit while keeping the wallet owner responsible for signing.

chaingpt — Plugin for Claude Code by ChainGPT-org

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.

Clone the repo

git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/chaingpt-org/chaingpt-claude-skill/chaingpt-claude-skill.svg)](https://agentmods.dev/plugins/chaingpt-org/chaingpt-claude-skill/chaingpt-claude-skill)

Your own site

<a href="https://agentmods.dev/plugins/chaingpt-org/chaingpt-claude-skill/chaingpt-claude-skill"><img src="https://agentmods.dev/badge/plugins/chaingpt-org/chaingpt-claude-skill/chaingpt-claude-skill.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server cost 2,819 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

chaingpt 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 8d 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-plugin/plugin.json · 40 lines

What it actually says

{
  "name": "chaingpt",
  "version": "1.22.2",
  "description": "The Web3 toolkit for Claude Code. AI-powered (ChainGPT chat / NFT / Solidity generator + auditor / crypto news / Solidity LLM) PLUS broad Web3: multi-chain wallet portfolios, token research, risk scanning, on-chain analytics, AI-enriched intel, MAINNET contract deployment with mandatory audit gate, MAINNET DEX trading (OpenOcean + 1inch v6 + CoW Protocol + Jupiter), MAINNET DeFi (Aave V3 + Lido + EigenLayer + Pendle + Morpho), MAINNET perps (Hyperliquid + Drift Solana), MAINNET Polymarket prediction-market data, MAINNET cross-chain bridging via Across Protocol v3, and multi-protocol portfolio snapshot. 45+ audited Solidity patterns + zero-credit mock server + daily live-API smoke CI. Custody-free.",
  "author": {
    "name": "ChainGPT",
    "url": "https://www.chaingpt.org"
  },
  "homepage": "https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk",
  "repository": "https://github.com/ChainGPT-org/chaingpt-claude-skill",
  "license": "MIT",
  "keywords": [
    "web3",
    "blockchain",
    "ai",
    "nft",
    "smart-contracts",
    "crypto",
    "defi",
    "chaingpt",
    "solidity",
    "mcp",
    "dexscreener",
    "goplus",
    "etherscan",
    "wallet",
    "portfolio",
    "honeypot",
    "agent",
    "across",
    "1inch",
    "cowswap",
    "pendle",
    "morpho",
    "drift",
    "solana"
  ],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json"
}

Contents

What it installs

The manifest is a name and a version. 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 2,819 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

2 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 40 lines scan A 25c6db144d63

Subscribe to this mod's changes

chaingpt is a plugin published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code Web3 and blockchain chaingpt defi ethereum mcp

chaingpt

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

perp-cli

krait

rugproof

coingecko-mcp-server

agentic-vault

humanizer