DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to hand off an unfinished task card to a new agent with Kander

Continue a half-done task with a different agent using only its card ID.

Who it is forA developer whose agent stopped partway through a card, or who wants to switch to another agent model mid-task.

The problemA stalled task blocks progress, and restarting it from scratch wastes the earlier work.

The outcomeA new agent picks up the card by its ID and continues the work the previous agent left.

What you need first

  • Git installed
  • At least one supported agent installed: Codex, Claude, Grok, Cursor, or Pi
  • A Homebrew install on macOS, or the Linux or Windows binary from the Releases page
  • GitHub CLI (gh) if you want to link a GitHub repository

Steps

  1. Stop the agent currently working on the card.
  2. Run kander to open the board, select the card, and press y to copy its task ID.
  3. Start a new agent with the Kander rules loaded.
  4. Prompt the new agent to take over and continue task card <TASK-ID>, replacing <TASK-ID> with the copied ID.
  5. Ask the agent for the current status of the card and check it on the board with r to refresh.

Prompt for your agent

In the dualface/kander repo, take over and continue task card <TASK-ID>. Report the card's current status, what has already been completed, and what remains. Verify the status against the board before you make any changes.

Caveat. The README describes handoff through the card ID but does not describe how a switched agent handles work in progress, so check the card state before continuing.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page