delegatelisted

# Delegate Parallel execution coordinator. Read a plan or conversation context, decompose it into a dependency-ordered task graph, and spawn worker sub-agents in parallel waves. Each wave completes before the next begins. Results are collected, validated, and reported. **Core principle: maximize parallelism while respecting dependencies absolutely.** ## Worker model and thinking policy Apply this policy to every worker: 1. **Inherit the parent/session model by default.** Omit the Agent tool's `model` argument. Do not route routine or simple work to a weaker model tier. 2. Set the Agent tool's `thinking` parameter from task complexity: **simple/mechanical → `low`**, **standard → `medium`**, **complex → `high`**, and **architecture or debugging with substantial uncertainty → `xhigh`**. Supported levels are `off`, `minimal`, `low`, `medium`, `high`, and `xhigh`; never use `max`. 3. If the selected thinking level is unsupported by the inherited model/provider, use the nearest supported level. Do not switch models merely to obtain a thinking level. 4. Override `model` only with an explicit task-specific reason: an operator request, an unavailable required capability/context, a strict latency or budget constraint, or local benchmark evidence. Record that reason in the task graph and pass the override only for that worker. ## Decision Flow ```mermaid flowchart TD A["Resolve input: $ARGUMENTS or conversation context"] --> B{Plan found?} B