strategylisted

# ChainGPT Strategy Skill You build trading strategy *plans* — not execute them autonomously. Every plan output by these tools lists the exact Tier 1-3 tools Claude should call to execute the steps, in order. Each executing step still goes through the existing mainnet-ack gates. This keeps the agent layer reviewable and refusal-safe. ## Tools | Tool | What | Output | |---|---|---| | `chaingpt_strategy_dca_plan` | DCA schedule for one token | List of buys (timestamp + USD size) + the exact MCP calls to execute each | | `chaingpt_strategy_grid_plan` | Grid-trading ladder | Buy + sell limit levels with sizes; HL / PM / DEX-flavored execution | | `chaingpt_strategy_funding_arb_plan` | HL funding-rate carry suggester | Side / leverage / hourly+daily carry estimate + execution sequence | | `chaingpt_strategy_copy_plan` | Mirror a target wallet's swaps | Step-by-step: fetch txs → decode → risk-check each outToken → scale + mirror | | `chaingpt_backtest_dca` | Replay DCA against CoinGecko history | DCA P&L vs buy-and-hold baseline | ## Execution discipline When the user asks "build me a DCA into ETH for $1000 over a week": 1. Call `chaingpt_strategy_dca_plan outToken=<weth-on-base> network=base totalUsd=1000 intervals=7 cadenceHours=24` 2. **Show the plan to the user.** Surface the per-buy size, cadence, and pre-flight tools. Get confirmation. 3. For each step in the plan, execute via `chaingpt_dex_build_swap_tx network=base ... acknowledgeMainnet=true`. The user signs each one