Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Trade Management Toolkit

    1

    Fewer know how much of each winner their exits actually keep.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Trade Management Toolkit

    Trade Management Toolkit

    Example session with this skill installed

    Using the Trade Management Toolkit skill: plan a buy at 2650.0 with a stop at 2647.5 using the runner rule, then replay my trades with my price bars and compare rules against what I actually did.

    • Read your context and instructions
    • Compiled the trade management toolkit

    Summary

    Plan (runner rule: 50% off at +1R, break-even, trail 1R):

    BUY entry 2650.0  stop 2647.5  (1R = 2.5 price units = 340 money)
      - partial: close 50.0% at +1R: 2652.5
      - move the stop to break-even after +1R: 2650.0
      - then trail the stop 1R behind the best price (it only moves in your favour)
    

    Replay on the included invented sample data (3 trades):

    rule                   trades   total R    avg R   win %  max DD R  give-back R
    fixed 2R                    3     6.000    2.000   100.0     0.000        0.233
    runner                      3     3.800    1.267   100.0     0.000        1.367
    break-even then 3R          3     3.000    1.000    33.3     0.000        1.667
    as taken                    3    -0.300   -0.100    33.3     1.500            -
    

    Next steps

    • Use your own trades and bars. Three invented trades prove nothing; aim for 30 or more.
    • This describes the past. It is not a forecast or financial advice.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Most traders know where they enter. Fewer know how much of each winner their exits actually keep.

    What it does

    • Plan: exact price levels for a trade from a rule (partial at +1R, break-even, trailing distance, final target, flatten time) and the money value of 1R.
    • Replay: runs one or more exit rules over your past trades and price bars and prints total R, average R, win rate, max drawdown in R and give-back for each rule, next to what you actually did.

    Built to be honest

    • Pessimistic on purpose: if one bar could have hit both your stop and a target, the stop comes first; a gap through the stop fills at the open.
    • 36 hand-computed price paths, long and short, all passing. Prices are exact decimals.
    • It never connects to a broker or places an order, and gives no entries or signals.

    Honest limits

    • It replays the past; it does not predict. A few trades prove little (aim for 30 or more).
    • You supply the price bars. Lower timeframes give more faithful results. Slippage and spread are ignored unless you set a cost.
    • The example files are invented data.

    Licence: for your own trading and business; no resale.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.

    No broker integration. Requires CSV files for trades and bars. Assumes worst-case execution if stop and target hit in same bar. No entry signal logic.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files

    Local only. Terminal/Shell runs scripts/trade_mgmt.py. Read Files reads the trades, price bars and rules files you point it at. No network access, no file writes, no environment-variable reads, no telemetry. It never connects to a broker.

    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This toolkit focuses exclusively on trade exits and risk management. It uses deterministic R-multiple logic and price replay to help you identify where you are leaving money on the table and which specific trailing stop or partial profit rules maximize your performance.

    The toolkit is a standalone Python-based utility that processes CSV and JSON files. While it doesn't require a specific AI agent framework to run, it is designed to be easily integrated into custom LLM-based trading agents that need a reliable engine for precise price calculations.

    You will receive the complete Python source code for the tool, a sample `trades.csv` and `bars.csv` to get you started, and a template `rules.json` file containing standard exit strategy configurations.

    Setup is minimal; you only need Python 3.8 or higher. Once you've added your trade history and price data to the provided CSV templates, you can run the 'plan' or 'replay' commands immediately without installing external libraries or connecting to broker APIs.

    The tool uses a conservative "worst-case" execution model: if both a stop-loss and a take-profit level are hit within the same price bar, the engine assumes the stop was hit first to ensure your backtesting results aren't overly optimistic.

    New in Trading & Investing