Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Session Handoff Pro

    2

    Generate high-fidelity technical handoff documents to transfer project state between agents, sessions, or teammates.

    $4.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Session Handoff Pro

    Session Handoff Pro

    Example session with this skill installed

    The context window is getting full. I've been refactoring the auth middleware and I need to stop here so another agent can finish it tomorrow. Write a handoff.

    • Read your context and instructions
    • Compiled the session handoff pro

    I have generated a technical handoff document in HANDOFF.md. It captures the current state of the auth middleware refactor, including the uncommitted changes in the JWT strategy and the specific test failures that need addressing next.

    HANDOFF.md

    1. Objective and state

    Goal: Decouple JWT validation logic from middleware/auth.ts into a standalone service.
    Status: In progress. The JwtService is created, but the passport strategy is currently broken.

    2. Decisions and why

    • Chose jsonwebtoken library over jose because the project already has it as a dependency and we want to minimize new bloat.
    • Chose to use a Class for JwtService to allow for easier dependency injection in future unit tests.

    3. The "do not redo" list

    • Tried to move secret loading into a static getter; failed because the config provider is initialized asynchronously. Do not attempt static loading for secrets.

    4. Exact state

    • Branch: refactor/auth-service
    • HEAD: a1b2c3d (Last commit: "feat: add base JwtService structure")
    • Files changed:
      • src/services/jwt.service.ts (Staged)
      • src/middleware/auth.ts (Dirty - logic partially removed)
      • package.json (Dirty - added @types/jsonwebtoken)

    5. Next actions with acceptance criteria

    1. Fix the import error in src/middleware/auth.ts regarding the JwtPayload type.
    2. Update src/config/passport.ts to use JwtService.validate().
    3. Run npm test src/middleware/auth.test.ts; must pass 12/12 tests.

    6. Open questions and risks

    • We need to confirm if the refresh_token logic should also move to this service or stay in the controller.
    • Ask User: "Should the new JwtService handle blacklisting, or will we keep that in Redis separately?"

    7. Verification recipe

    npm install
npm run build
npm test src/services/jwt.service.test.ts

    If build fails, check the generic types in jwt.service.ts line 42.

    Next steps

    • Review the HANDOFF.md file to ensure the "Next actions" align with your priorities.
    • Commit the handoff file along with your current dirty changes to preserve the state.
    • Start the next session by pointing the agent to this file.
    HANDOFF.md

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

    About this skill

    Stop losing context when switching between agents, sessions, or teammates. This skill eliminates the "re-discovery tax" by generating high-fidelity handoff documentation that allows a fresh session to resume work with zero friction. It replaces vague summaries with technical state reports, ensuring dead ends are documented and next steps are actionable.

    session-handoff-comparison.png

    What it does

    • State tracking captures the current objective and categorizes status as Done, In progress, or Blocked with evidence.
    • Decision logging records technical choices and rationales to prevent the next session from re-litigating design decisions.
    • Dead-end documentation creates a "do not redo" list of failed attempts and abandoned hypotheses to save hours of wasted time.
    • Environment mapping lists branches, HEAD commits, dirty files, and active ports or environment variables.
    • Actionable tasking generates ordered next steps with specific file paths and concrete acceptance criteria.
    • Verification recipes provides the exact commands needed to confirm the state matches the documentation upon resume.

    How it works

    1. Analyze current state by scanning the file system, git history, and recent chat history to gather technical context.
    2. Apply the handoff method to populate the seven mandatory sections: Objective, Decisions, Do Not Redo, State, Actions, Risks, and Verification.
    3. Draft the document into HANDOFF.md or a versioned docs/handoffs/ file depending on the project structure.
    4. Finalize and link by archiving previous handoffs and ensuring the new file is ready to be committed with the current work.

    Frameworks & tools

    This skill is platform-agnostic and works with any repository. It uses standard Markdown for documentation and relies on access to local git state, file structures, and terminal output.

    Why this beats prompting it yourself

    Generic prompts produce narrative summaries that miss critical technical details like dirty file states or failed debugging attempts. This skill enforces a strict seven-section architecture that ensures no information, especially what NOT to try again is lost during the transition.

    Use cases

    • Context management when your agent's context window is full and you need to start a fresh session.
    • Shift changes when passing a complex feature implementation to a human teammate or another specialized agent.
    • Task pausing when stopping work for the day and needing to resume tomorrow without mental overhead.
    • Agent handoffs when moving from a research-focused agent to a coding-focused agent.

    Known limitations

    Requires file system access to write the handoff document. Does not store secrets or credentials, only identifies where they are located.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed 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 scanned

    Verified clean 6 days ago

    • Passed all security checks, Safe to install

    Listed6 days ago
    Updated4 days ago

    What's inside

    Frequently Asked Questions