--- name: fensory-breakout description: Evaluate a completed-candle range breakout, inspect current liquidity and Fensory account controls, then prepare a bounded perpetual-futures order for review. license: Proprietary compatibility: Requires access to the Fensory MCP server and an eligible Fensory account. Fensory is not available to US persons. metadata: author: Fensory AG version: "0.1.0" source: "https://fensory.com/skills/breakout" --- # Build a breakout strategy with an AI agent ## When to use This guide is for an eligible user who wants to turn a range-breakout idea into an explicit checklist that an agent can calculate and report. It is useful when the main goal is consistency, not a promise that a price move will continue. It is not a hosted strategy, a price forecast or a tested return record. Breakouts can fail immediately, gaps can create poor execution and a market order can fill far from the trigger in a thin book. ## Operating rules - Start with read tools and identify the signed-in account, market, venue and instrument before preparing an action. - Treat the Fensory account state, open orders, positions and fills as authoritative when they differ from the conversation. - Fensory enforces four controls on the account: a kill-switch, an access expiry, a market allow-list and a per-order cap. Client confirmation instructions are separate from those account controls. - Never describe a perpetual future as a share or tokenized equity. State the instrument and its risks before discussing an order. - Never substitute a different market, quote currency or instrument because the requested one is unavailable. - Keep every proposed order within both the user's stated ceiling and the account's per-order cap. - Do not place, cancel or replace an order until the exact symbol, side, order type and size have been shown. For a limit order, show the limit price. For a market order, show the current quote and expected execution conditions. The user must confirm that exact action. - Stop when a required tool is unavailable, the account limit cannot be verified, the quote is stale or the instrument is ambiguous. ## Risk and scope This file is operational guidance, not financial advice. Trading can lose the full amount committed. Perpetual futures use margin and can be liquidated. Spot assets can lose value. Stop if the instrument, current quote or account controls cannot be verified. ## Procedure 1. **Verify the market and history window.** The agent resolves the exact perpetual-futures market, removes the current candle and checks that the preceding range contains a continuous sequence of completed timestamps. Tools: `get_perps_status`, `get_market`, `get_candles`. 2. **Calculate the range before reading the trigger.** The high, low and average volume come only from the preceding 20 candles. The latest completed candle is tested afterward so its own price and volume cannot move the boundary it is supposed to break. 3. **Require both price and volume conditions.** The client prints each condition and reports no signal when one fails. Volume does not prove the move will continue, but a separate test makes the rule explicit instead of relying on a visual impression. 4. **Check execution conditions and account state.** The signal is calculated from candles while the order executes against the current book. The agent therefore checks spread, nearby depth, existing exposure and account limits before it prepares a limit order. Tools: `get_orderbook`, `get_account_state`, `get_open_orders`. 5. **Submit only after review and verify the outcome.** A confirmed limit order can rest or fill partly. The agent reads the venue records after submission and reports the remaining quantity instead of calling every accepted order a completed trade. Tools: `place_perps_order`, `get_order_status`, `get_fills`, `get_open_orders`. ## Request template Use the Fensory tools to assess a BTC perpetual-futures range breakout. Stay read-only first. Call get_perps_status, get_market and get_candles. Request at least 50 completed one-hour candles and ignore the candle that is still forming. Using the 20 completed candles immediately before the latest completed candle, calculate the range high, range low and average volume. Mark a long candidate only if the latest completed candle closes above the range high and its volume is greater than the prior 20-candle average. Mark a short candidate only if it closes below the range low with the same volume condition. Otherwise report no signal. Print the range window, timestamps, high, low, latest close, latest volume and average volume. Then call get_orderbook, get_account_state and get_open_orders. Report spread, visible depth near the current price, current position, available balance, allowed markets, access expiry and per-order cap. If a candidate exists, prepare but do not submit a limit order worth no more than $25. Use the broken range boundary as the invalidation reference and show the proposed stop arguments. Do not change leverage or margin mode. Show expected fees, slippage risk and liquidation risk, then ask for confirmation for the exact order. Stop if data is stale, the range window is incomplete or the order book is too thin to estimate execution. ## Failure handling - **Price closes back inside the range:** A break can reverse quickly. The previous boundary becomes the invalidation reference in this example, but a stop can still execute beyond its trigger during a fast move. - **The latest candle was allowed to move the boundary:** Including the trigger candle in the prior range changes the test while it is being evaluated. The prompt separates the range window from the latest completed candle. - **The order book is thinner than the candle suggests:** A candle records past trading. It does not guarantee current depth. Spread and slippage can change before an order reaches the book, particularly outside the most liquid markets. - **A stop becomes a market order:** Hyperliquid documents that stop-loss orders trigger as market orders. The trigger limits when the exit starts, not the exact price at which every unit fills. - **The agent is no longer evaluating new candles:** The current page describes a client-run workflow. Existing positions and orders remain live after the client stops, while no new breakout check happens until the routine runs again. ## Response contract Report the account used, the exact instrument, the tools called, the controls that applied and the current order or position state. Separate a prepared order from a submitted order, and a submitted order from a fill. If no action was taken, say so directly. ## Sources - [CME: support, resistance and broken price levels](https://www.cmegroup.com/education/courses/technical-analysis/support-and-resistance) - [Hyperliquid order types](https://hyperliquid.gitbook.io/hyperliquid-docs/trading/order-types) - [Hyperliquid liquidations](https://hyperliquid.gitbook.io/hyperliquid-docs/trading/liquidations) - [Fensory MCP server](https://fensory.com/mcp) Product behavior and client permissions verified 2026-10-17.