From chaingpt
Executes DEX trades on mainnet across EVM chains (via OpenOcean, 1inch, CoW Protocol) and Solana (via Jupiter). Builds unsigned transactions for external signing with mandatory risk checks on buy tokens.
How this skill is triggered — by the user, by Claude, or both
Slash command
/chaingpt:tradeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You execute real mainnet DEX trades on behalf of the user. **The plugin never holds keys.** Your job is to:
You execute real mainnet DEX trades on behalf of the user. The plugin never holds keys. Your job is to:
chaingpt_research_token — confirm the user is buying the token they think
chaingpt_risk_token — GoPlus + Honeypot check on the OUT token (MANDATORY)
chaingpt_dex_quote — expected output, price impact, route
│ (surface to user with USD-denominated cost and slippage)
▼
chaingpt_dex_approve_tx — if inToken is ERC-20 and current allowance is insufficient (requires acknowledgeMainnet: true — approvals delegate spend authority)
│ (user signs + broadcasts the approval)
▼
chaingpt_dex_build_swap_tx — REFUSES mainnet unless acknowledgeMainnet=true
│ (user signs + broadcasts the swap)
▼
chaingpt_onchain_tx hash=… — confirm execution, surface received-amount
Pipeline for Solana is identical but two-step (no approval needed):
chaingpt_risk_token (on Solana outToken)
chaingpt_dex_jupiter_quote
chaingpt_dex_jupiter_build_swap_tx (requires acknowledgeMainnet)
chaingpt_dex_build_swap_tx with acknowledgeMainnet: true unless the user has explicitly confirmed they want to swap on mainnet with the specific amounts and tokens you echoed back.chaingpt_dex_quote before asking for confirmation.chaingpt_risk_token raises a honeypot or cannot-sell-all flag, REFUSE the swap. Surface the flag and require an explicit user override before re-running.chaingpt_audit_contract on the outToken's contract if it's a freshly-deployed or unverified contract. The audit gate is the ChainGPT-native moat.chaingpt_dex_build_swap_tx returns:
{
"chainId": 8453,
"to": "0x6352a56caadc4f1e25cd6c75970fa768a3304e64", // OpenOcean router on Base
"data": "0x90411a32…",
"value": "0x0", // non-zero for native-in swaps
"gas": "0x4c4b40",
"gasPrice": "0x4a817c800"
}
The user pastes this into MetaMask's "send transaction" / Rabby's import-tx feature, or programmatically calls wallet.sendTransaction(tx) if they have a script.
EVM: ethereum, base, arbitrum, optimism, polygon, bsc, avalanche, blast, linea, scroll. Solana: mainnet only.
OpenOcean is the default because it's keyless and covers all 10 EVM chains. Two alternatives are wired in for specific use cases:
chaingpt_dex_1inch_quote / chaingpt_dex_1inch_swap_tx)ONEINCH_API_KEY (free tier at https://1inch.dev → Developer Portal). Without the key, the tool returns a setup hint and falls back to OpenOcean.spender for chaingpt_dex_approve_tx, with acknowledgeMainnet: true).chaingpt_dex_cow_create_order / chaingpt_dex_cow_submit_signed_order)chaingpt_dex_cow_submit_signed_order POSTs it to the CoW API and returns an order UID trackable on https://explorer.cow.fi.0xC92E8bdf79f0507f65a392b0ab4667716BFE0110 (NOT the Settlement contract). One-time approval per token.acknowledgeMainnet=true. Once signed and submitted, solvers WILL execute the order — there's no client-side broadcast step to cancel at.Trading itself burns 0 ChainGPT credits — OpenOcean and Jupiter are free. The pre-flight chaingpt_risk_token is also free (GoPlus). The optional chaingpt_audit_contract step burns 1 credit. The credit funnel for this skill comes from upstream calls (research / news / signals) the user makes before deciding to trade.
npx claudepluginhub chaingpt-org/chaingpt-claude-skill --plugin chaingptProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.