Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Handoff-MCP

    1

    Durable session memory and project-scoped TODO management for AI agents via MCP.

    Free

    1 useSecurity scanned
    Handoff-MCP

    Handoff-MCP

    Example session with this skill installed

    I'm done for the day. Can you save a handoff for the auth refactor? I finished the JWT logic in auth.ts but still need to update the middleware.

    • Read your context and instructions
    • Compiled the handoff-mcp

    I have recorded the current state of the auth refactor and updated the project TODO list. The handoff includes the completed JWT logic and specific instructions for the middleware updates.

    Project Handoff: Auth Refactor

    ItemTypeStatusDetails
    JWT ImplementationTaskCompletedLogic implemented in src/lib/auth.ts.
    Middleware UpdateTaskPendingNeed to integrate new JWT verification in src/middleware.ts.
    Session StateHandoffActiveRefactor is 50% complete. Auth service is stable but not hooked to routes.
    Context CompactSummarySavedCompacted current discussion on token expiration into the handoff store.

    Next steps

    • Run handoff_list when you return to see the full implementation details.
    • Execute todo_update for the middleware task once the route protection is verified.
    • Review the auth.ts exports to ensure they match the middleware requirements.

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

    About this skill

    LLM context windows reset every session, causing agents to lose track of progress, pending tasks, and architectural decisions. This skill provides a durable memory layer for your agent using a project-local MCP server to ensure continuity between sessions.

    What it does

    • Persistent TODO tracking manages concrete tasks with priorities, tags, and status updates directly in the project scope.
    • Session handoffs record the current state, key decisions, and specific file paths at the end of a work interval.
    • Context management generates reports on active context and compacts bloated sessions into digestible summaries.
    • Durable storage keeps all breadcrumbs and tasks in a local store independent of the conversation history.

    How it works

    1. Use handoff_list and todo_list at the start of a new session to restore project state.
    2. Add new tasks via todo_add as requirements emerge during development.
    3. Call context_report when the prompt window feels cluttered to identify what to prune.
    4. Execute handoff_add before closing the session to leave instructions for the next agent instance.

    Frameworks & tools

    This skill requires the Handoff MCP server. It is designed for use with Model Context Protocol compatible environments like Claude Desktop, Cursor, or specialized IDE agents.

    Why this beats prompting it yourself

    Relying on chat history for project state leads to hallucinations as the context window fills up. This skill moves project tracking into a structured local database that persists even if you clear your chat or switch models.

    Use cases

    • Resuming a complex refactoring job after a break without re-explaining the plan.
    • Coordinating between multiple specialized agents by leaving breadcrumbs in a shared store.
    • Managing long-running project roadmaps directly within the developer environment.

    Known limitations

    Requires a running Handoff MCP server. Storage is repository-scoped and does not synchronize across different machines unless the local store is shared.

    Requires a functioning Handoff MCP server installation. Context compaction does not delete actual client conversation history.

    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 1 month ago

    • Free with an Agensi account

    Requires

    Handoff MCP
    Handoff Install MCP
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Standard LLM chat histories are transient and lose detail as they fill up. This skill provides a dedicated, project-local database that persists tasks and architectural state even if you clear your chat, switch models, or restart your IDE.

    This skill is built for any environment that supports the Model Context Protocol (MCP), including Claude Desktop and Cursor. It works best with developer-focused agents that have filesystem access to manage the local storage.

    When you purchase this skill, you receive the MCP server implementation and the specific tool definitions (such as handoff_add and todo_list) required to integrate durable memory into your agent's workflow.

    To use this skill, you must have the Handoff MCP server running locally. The data is stored within your specific project directory, ensuring that your agent’s memory is scoped only to the codebase you are currently working on.

    Yes, since the state is stored in a structured local file within your repository, different agents (or even different LLM models) can read the same handoff reports and TODO lists to stay aligned on project progress.

    handoff-mcp is designed for local-first privacy; your project notes and task lists stay on your machine within the local MCP store and are not uploaded to a central cloud database.

    New in LLM Ops