Task Orchestrator

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Task Orchestrator

    1

    Persistent, hierarchical task and goal management for agents using MCP and LokiDB.

    Free

    1 useSecurity scanned

    Task Orchestrator

    Example session with this skill installed

    I want to start a new goal for the 'auth-service' repo to implement OAuth2. Create the goal and add two tasks: 'Setup provider' and 'Write middleware' with subtasks for JWT and Session logic.

    • Read your context and instructions
    • Compiled the task orchestrator

    I have successfully initialized the goal and established the task hierarchy for the auth-service repository. The tasks are persisted and follow the dot-notation structure for dependency tracking.

    Task Orchestration: OAuth2 Implementation

    IDTask DescriptionStatusParent ID
    1Setup providerOPEN-
    2Write middlewareOPEN-
    2.1Implement JWT logicOPEN2
    2.2Implement Session logicOPEN2

    Goal ID: goal_17389204
    Repository: auth-service
    Status: 0/4 tasks completed

    Next steps

    • Start working on the provider setup by calling complete_task_status for ID 1 when finished.
    • Use get_tasks with includeSubtasks: "recursive" to see the full tree at any time.
    • If you need to add more granular steps to the JWT logic, use add_tasks with parentId: "2.1".

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

    About this skill

    Maintaining complex state across multiple AI sessions is difficult when relying only on context windows. This skill implements a hierarchical task management system via an MCP server, providing persistent, structured storage for goals and subtasks.

    What it does

    • Goal management creates durable top-level objectives associated with specific repositories.
    • Hierarchical tasking uses dot-notation IDs like 1.2.1 to organize work into deeply nested trees.
    • Transactional updates ensure task batches are added or modified atomically to prevent state corruption.
    • Dependency enforcement prevents marking parent tasks as complete while subtasks remain open.
    • Persistent storage utilizes LokiDB to ensure your task lists survive agent restarts or session timeouts.

    How it works

    1. Initialize a goal using the create_goal tool to establish a new project scope.
    2. Build the task tree by passing nested subtask arrays to add_tasks in a single call.
    3. Query progress with get_tasks to retrieve first-level or recursive task lists.
    4. Update status via complete_task_status, optionally closing entire branches at once.

    Frameworks & tools

    This skill requires Node.js 18+ and pnpm. It is built as an MCP server using the Model Context Protocol and stores data locally using LokiDB.

    Why this beats prompting it yourself

    Standard prompts lose task context as conversations grow long, leading to forgotten requirements or duplicate work. This skill moves the "todo list" out of the volatile context window and into a structured database with enforced parent/child logic.

    Use cases

    • Manage multi-step refactoring projects across several days of work.
    • Orchestrate sub-agents by assigning specific dot-notation task IDs.
    • Maintain a durable project roadmap that persists through agent crashes.

    Known limitations

    Does not support goal deletion or inter-goal dependencies. A dedicated progress visualization UI and complex cross-task orchestration are currently not implemented.

    Requires Node.js 18+ and pnpm. Does not support goal deletion or inter-goal dependencies. No built-in progress visualization UI.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Requires

    Node.js
    Git

    Permissions

    Terminal / Shell
    Network Access

    Local persistence only: the server writes a LokiDB file on disk for task state. It makes no network calls and requests no credentials.

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill moves project state out of the volatile context window and into a persistent LokiDB database, preventing the AI from 'forgetting' goals or repeating work during long-running projects.

    The skill is built on the Model Context Protocol (MCP), making it compatible with any AI agent or IDE (like Claude Desktop or Cursor) that supports the MCP standard.

    Yes, the 'add_tasks' tool supports nested arrays, allowing you to create complex, multi-level task trees with dot-notation IDs (e.g., 1.1.2) in a single transactional call.

    The skill enforces dependency logic, meaning the agent cannot mark a parent task as 'Complete' until all of its associated subtasks have been finished or closed.

    You will need Node.js 18+ and pnpm installed; once configured as an MCP server, the skill handles all database initialization and state management automatically.

    The skill currently focuses on single-goal trees; while you can manage multiple independent goals, it does not currently support linking tasks across different top-level goals.

    New in Agents & Orchestration