ChainGPT-org/chaingpt-claude-skill
154 Web3 MCP tools for Claude Code, custody-free. Plus an agent wallet prompt injection can't drain: per-tx, daily, and on-chain (ERC-4337) spending caps the model can't bypass. EVM + Solana + Tron DEX/DeFi, perps, prediction markets, contr
stack: TypeScript
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~4.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ npx degit ChainGPT-org/chaingpt-claude-skill/agents ./rig-chaingpt-claude-skill/agents $ npx degit ChainGPT-org/chaingpt-claude-skill/skills ./rig-chaingpt-claude-skill/skills $ npx degit ChainGPT-org/chaingpt-claude-skill/hooks ./rig-chaingpt-claude-skill/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit ChainGPT-org/chaingpt-claude-skill/skills/aa .claude/skills/aa $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/agent-wallet .claude/skills/agent-wallet $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/base .claude/skills/base $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/bridge .claude/skills/bridge $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/chaingpt .claude/skills/chaingpt $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/dashboard .claude/skills/dashboard $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/debug .claude/skills/debug $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/defi .claude/skills/defi $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/deploy .claude/skills/deploy $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/drift .claude/skills/drift $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/hackathon .claude/skills/hackathon $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/hyperliquid .claude/skills/hyperliquid $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/playground .claude/skills/playground $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/polymarket .claude/skills/polymarket $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/research .claude/skills/research $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/scheduled-autonomy .claude/skills/scheduled-autonomy $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/security .claude/skills/security $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/solana .claude/skills/solana $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/strategy .claude/skills/strategy $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/trade .claude/skills/trade $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/tron .claude/skills/tron $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/trustless-agents .claude/skills/trustless-agents $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/update .claude/skills/update $ npx degit ChainGPT-org/chaingpt-claude-skill/skills/x402 .claude/skills/x402
$ curl -fsSL --create-dirs -o .claude/agents/contract-auditor.md https://raw.githubusercontent.com/ChainGPT-org/chaingpt-claude-skill/main/agents/contract-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/defi-trader.md https://raw.githubusercontent.com/ChainGPT-org/chaingpt-claude-skill/main/agents/defi-trader.md $ curl -fsSL --create-dirs -o .claude/agents/web3-researcher.md https://raw.githubusercontent.com/ChainGPT-org/chaingpt-claude-skill/main/agents/web3-researcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| chaingpt env: CHAINGPT_API_KEY | local / custom | 2.5k |
Skills (24)
aaagent-walletbasebridgechaingptdashboarddebugdefideploydrifthackathonhyperliquidplaygroundpolymarketresearchscheduled-autonomysecuritysolanastrategytradetrontrustless-agentsupdatex402
Subagents (3)
| contract-auditor | Solidity contract specialist for the generate → audit → fix → deploy lifecycle. Use when writing, reviewing, auditing, or deploying smart contracts. Enforces the audit-before-deploy discipline and nev |
| defi-trader | Disciplined DeFi execution specialist for swaps, bridges, lending, LP/yield moves, and perps order prep. Use when the user wants to actually DO something on-chain. Runs mandatory pre-flight checks, re |
| web3-researcher model: haiku | Read-only Web3 research analyst. Use for <redacted>, market scans, wallet forensics, yield comparisons, perps/funding analysis, and prediction-market odds — anything that answers a question without mo |
Similar rigs
patrickjaja/claude-desktop-extra
Unofficial Linux packages for Claude Desktop AI assistant with automated updates.
Skill Collector 9.2k tok · · Q5
codifydoo/gatehand
Unattended Claude coding agents for a GitHub repository: coder, fixer, Claude review and merge gate, as a Claude Code plugin
Pragmatist 1.6k tok · · Q0
kennedykjj/shipfloor
Shipfloor - a software factory.
Pragmatist 375 tok · · Q16
umararshad4/honey-stack
Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.
Skill Collector 2.3k tok · · Q0