> For the complete documentation index, see [llms.txt](https://docs.cod3x.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cod3x.org/terminal-overview/goals-task-management/goals-overview.md). # Goals Overview Each goal in Cod3x has an **Overview** tab that provides full visibility into its performance, configuration, and runtime behavior. *** #### Task Prompt Every goal begins with a **Task Prompt** — a structured breakdown of what the agent must execute when the goal runs. It serves as the core instruction set, combining your natural-language description with tool-based steps and execution logic. *** #### Performance Metrics At the top of the Overview, you’ll find live statistics summarizing execution results: * **Total Runs** – The number of completed goal executions. * **Success Rate** – The percentage of runs completed without errors or interruptions. * **Average Credits** – The mean compute cost per run. These metrics help identify performance efficiency and optimization opportunities across different goals and models. *** #### Configuration Details Below performance metrics, the configuration panel summarizes how the goal is set up: * **Goal Type** – Defines the category (Trading, Research). * **Strict Tools Mode** – If enabled, limits the agent to specific pre-approved tools only. * **Requires Open Positions** – Restricts goal execution to cases where the agent already holds an open trade. Configuration is editable at any time, allowing rapid iteration between model types, toolsets, and goal dependencies. *** #### Run History The **Last Run** section logs current and previous executions: * **Status** – Indicates whether a goal is active, paused, or completed. * **Run Number** – Sequential count of goal executions. * **Credits Used** – Compute credits consumed in the latest run. * **Duration** – Time elapsed for the goal’s execution. Click **View Details** to inspect the full execution trace, including tool calls, results, and any agent reasoning used during the process. *** #### Suggested Tools Cod3x recommends tools based on the goal’s task prompt and prior usage.\ Examples include: * `GeHLMarketInfoTool` * `HLPositionManagerTool` * `UpdateGoalHistoryTool` * `ListGoalsTool` These serve as quick links to refine your goal’s capabilities or extend automation workflows. *** #### Deleting a Goal At the bottom of the Overview, you can permanently remove a goal and its full run history.\ This action cannot be undone and should only be performed when you’re certain the goal is no longer needed. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.cod3x.org/terminal-overview/goals-task-management/goals-overview.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.