Dojo Swarm.prompt

---
mode: agent
description: 'Run the dojo pipeline with parallel sub-agents for execution.'
---
<!-- Auto-generated by scripts/regen-prompts.sh from scripts/pipeline.tsv. Do not edit by hand. -->

Run the **dojo swarm** — the parallel variant of the mandatory workflow — for the goal I give you.

Scaffold with `bash scripts/sprint.sh start "<goal>" --swarm`, then walk the same phases:

1. **BRAINSTORM** — read [`skills/brainstorming/SKILL.md`](../../skills/brainstorming/SKILL.md): Socratic refinement into an approved design
2. **WORKTREE** — read [`skills/using-git-worktrees/SKILL.md`](../../skills/using-git-worktrees/SKILL.md): Isolated workspace on a feature branch
3. **PLAN** — read [`skills/plan-before-code/SKILL.md`](../../skills/plan-before-code/SKILL.md): Bite-sized tasks written to tasks/todo.md
4. **EXECUTE** — read [`skills/executing-plans/SKILL.md`](../../skills/executing-plans/SKILL.md): One task at a time, verifying each before the next
5. **TEST** — read [`skills/test-writing/SKILL.md`](../../skills/test-writing/SKILL.md): RED then GREEN then REFACTOR for every behaviour change
6. **REVIEW** — read [`skills/requesting-code-review/SKILL.md`](../../skills/requesting-code-review/SKILL.md): Self-review the diff against the plan
7. **FINISH** — read [`skills/finishing-a-development-branch/SKILL.md`](../../skills/finishing-a-development-branch/SKILL.md): Verify, decide the merge, clean up the branch
8. **LEARN** — read [`skills/self-improvement/SKILL.md`](../../skills/self-improvement/SKILL.md): Log lessons, promote patterns, update the memory vault

Coordination rules for the parallel section (read skills/dispatching-parallel-agents/SKILL.md):

- Keep **BRAINSTORM, WORKTREE, and PLAN sequential** — design and task-splitting happen once, up front.
- Split **EXECUTE + TEST** into independent board tasks, one per sub-agent; no two sub-agents touch the same files.
- Respect the subagent depth/concurrency limits in AGENTS.md.
- **Fan in at REVIEW**: collect the sub-agents' diffs and self-review the combined change against the plan.
- Run a **single central** `bash scripts/sprint.sh finish` — the gate and merge decision happen once, not per sub-agent.