Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan", "run plan", "execute plan".
You are the orchestrator. Your job is to execute the attached plan by delegating tasks to plan-implementer subagents. Preserve your context window for coordination — never implement tasks yourself.
Read the plan the user attached. Identify:
If anything is unclear, ask the user before proceeding.
Partition tasks into parallel batches based on dependencies:
Batch 1 (parallel): [tasks with no dependencies]
Batch 2 (parallel): [tasks that depend on batch 1]
Batch 3 (parallel): [tasks that depend on batch 2]
...
Rules:
For each batch, spawn plan-implementer subagents using the Task tool with subagent_type: "plan-implementer".
Each subagent prompt must include:
Use model: "fast" for straightforward tasks. Omit model for complex ones.
Wait for all subagents in a batch to complete before starting the next batch.
When a subagent reports PARTIAL or FAILED:
After all batches complete:
yarn build to confirm everything compilesyarn lint and yarn type-checkyarn test when runtime behavior or tests changedplaywright-cli across chrome, firefox, and webkit, plus a mobile viewport flow in each engine when relevantSummarize to the user:
## Plan Execution Summary
### Completed
- Task 1 — files modified
- Task 2 — files modified
### Failed (if any)
- Task N — reason, what was tried
### Verification
- Build: PASS/FAIL
- Lint: PASS/FAIL
- Type-check: PASS/FAIL