work-item-decompose

<guidelines>
  - Prefer vertical slices over horizontal layers
  - Start with foundation pieces (models, schemas)
  - End with integration pieces (API, UI)
  - Keep each item focused on ONE concern
</guidelines>

<complexity level="low">
  - Single file or few files
  - Well-understood pattern
  - No external dependencies
  - Examples: bug fix, config change, simple utility
</complexity>

<complexity level="medium">
  - Multiple files
  - Standard patterns with some decisions
  - May touch existing code
  - Examples: new endpoint, new component, feature addition
</complexity>

<complexity level="high">
  - Architectural decisions required
  - Security or data implications
  - Core system changes
  - Examples: auth system, payment flow, database migration
</complexity>

<bias_table>
  | Raw Complexity | autonomous | balanced | controlled |
  |----------------|------------|----------|------------|
  | low            | autopilot  | autopilot| confirm    |
  | medium         | autopilot  | confirm  | validate   |
  | high           | confirm    | validate | validate   |
</bias_table>

<note>
  This allows user preference to shift thresholds:
  - autonomous: trusts AI more, fewer checkpoints
  - balanced: standard behavior (default)
  - controlled: more human oversight
</note>

<check if="circular dependency detected">
  <output>
    Warning: Circular dependency detected between {item-a} and {item-b}.
    Suggest splitting into smaller items or reordering.
  </output>
</check>

  **Total**: {count} work items
  **Estimated**: {low} autopilot, {medium} confirm, {high} validate

  **Work Item Details**:

  {for each item}
  {n}. **{title}** ({mode}) — {description}
  {/for}

  ---

  Approve this plan? [Y/n/edit]
</output>

  ---

  Ready to plan execution scope? [Y/n]
</output>
<check if="response == y">
  <route_to>builder-agent (run-plan)</route_to>
</check>