# AI use cases for Kander (dualface/kander) Repo: [dualface/kander](https://github.com/dualface/kander) | Use cases: 4 | Page: https://dedupedai.com/use-cases/dualface-kander/ Kander is a kanban board, run from the terminal, that coordinates multiple AI coding agents in isolated git worktrees and gates their work through independent reviewer agents. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run several coding agents on one backlog in parallel: https://dedupedai.com/use-cases/dualface-kander/run-parallel-agents-without-write-conflicts/ - Block agent changes that fail an independent review: https://dedupedai.com/use-cases/dualface-kander/gate-agent-code-with-independent-review/ - Import GitHub issues as board cards and track them: https://dedupedai.com/use-cases/dualface-kander/turn-github-issues-into-board-cards/ - Hand off an unfinished task card to a new agent: https://dedupedai.com/use-cases/dualface-kander/hand-off-an-unfinished-task-to-a-new-agent/ ## How to run several coding agents on one backlog in parallel with Kander Repo: [dualface/kander](https://github.com/dualface/kander) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Split a backlog into task cards and let agents work on them at once without write conflicts. **Who it is for:** A solo developer with a list of features or fixes who wants several AI agents working at the same time, and who is tired of agents editing the same files. **The problem:** Running several coding agents in one checkout causes branch overlaps, file clashes, and lost work. **The outcome:** Multiple task cards run in their own worktrees, and the board schedules them so overlapping work does not run at once. ### Steps 1. Install Kander on macOS with `brew install dualface/tap/kander`, or download the Linux or Windows build from the Releases page. 2. Run `kander doctor` to check Git, your agents, launchers, and rules configuration. 3. Run `kander` to open the terminal kanban board. 4. Start an agent session, describe one requirement with its goal and acceptance criteria, and confirm the agent should launch it through the kanban flow. 5. Repeat for each requirement, then check status on the board and use `/` to filter cards. ### Prompt to paste into your agent ```text In the dualface/kander repo, load the Kander rules and create one task card for the requirement with clear acceptance criteria, then confirm it was launched through the kanban flow. Report the card ID and its status. Verify that the card appears on the board with its own isolated workspace. ``` ### Caveat The README says Kander uses Git Worktrees and tmux or herdr containers, so you need those environments set up for the parallel runs to behave as described. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/dualface-kander/run-parallel-agents-without-write-conflicts/ ## How to block agent changes that fail an independent review with Kander Repo: [dualface/kander](https://github.com/dualface/kander) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Send each agent's finished work to a separate reviewer agent before it is delivered. **Who it is for:** A developer who lets agents write production code and does not want to merge work that only looks correct in tests. **The problem:** Agents can report green tests while the code still has semantic or state-machine bugs. **The outcome:** Each task passes through a reviewer that did not write the code, and must-fix findings stop delivery until they are resolved. ### Steps 1. Install Kander with `brew install dualface/tap/kander` on macOS, or use the Linux or Windows build from Releases. 2. Run `kander doctor` to confirm your agents and rules configuration are ready. 3. Create a task card through an agent session and confirm it launches through the kanban flow. 4. Let the execution agent finish, then wait for the review stage to run before the card is marked complete. 5. Read the review result on the card and read the review disposition and completion gate notes in docs/review-disposition.md before accepting the work. ### Prompt to paste into your agent ```text In the dualface/kander repo, read docs/review-disposition.md and then review the task card on the board. Report whether the review stage found must-fix issues and whether the completion gate passed. Verify that the reviewer result is recorded on the card before you call the task done. ``` ### Caveat The 49% and 1,694 review figures come from the author's own production use, and the README does not say how they would apply to your project. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/dualface-kander/gate-agent-code-with-independent-review/ ## How to import GitHub issues as board cards and track them with Kander Repo: [dualface/kander](https://github.com/dualface/kander) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Pull open GitHub issues into the kanban board and assign them to agents. **Who it is for:** A maintainer with a GitHub repo full of issues who wants agents to pick them up without copying each issue by hand. **The problem:** Moving issues into a board by hand is slow, and progress gets out of sync with the issue tracker. **The outcome:** Selected issues become task cards on the board, and their progress can be synced back from the board. ### Steps 1. Install the GitHub CLI and sign in with `gh auth login` so Kander can reuse your credentials. (inferred, check the README) 2. Install Kander with `brew install dualface/tap/kander` on macOS, or use the Linux or Windows build from Releases. 3. Run `kander` to open the terminal board. 4. Press `g` to open the GitHub Issues overlay, then choose the issues to import with one click. 5. Start the imported cards with an agent session or from the task action menu opened with `m`. ### Prompt to paste into your agent ```text In the dualface/kander repo, use the GitHub integration to import the open issues from as task cards. Report how many cards were created and their IDs. Verify that each card links back to its source issue. ``` ### Caveat The README says Kander does not store a token and reuses gh credentials, so the access it gets is whatever your gh login already has. Risk, credentials: Kander reuses your local gh login, so any agent running through Kander acts with the same GitHub access as your gh account. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/dualface-kander/turn-github-issues-into-board-cards/ ## How to hand off an unfinished task card to a new agent with Kander Repo: [dualface/kander](https://github.com/dualface/kander) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Continue a half-done task with a different agent using only its card ID. **Who it is for:** A developer whose agent stopped partway through a card, or who wants to switch to another agent model mid-task. **The problem:** A stalled task blocks progress, and restarting it from scratch wastes the earlier work. **The outcome:** A new agent picks up the card by its ID and continues the work the previous agent left. ### 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 , replacing 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 to paste into your agent ```text In the dualface/kander repo, take over and continue task card . 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/dualface-kander/hand-off-an-unfinished-task-to-a-new-agent/