Milestone Planning (Ultraplan)

Decomposes a complex task into milestones by spawning 5 parallel reviewer agents, synthesizing their independent analyses, and producing a milestone dependency DAG.

Core Principle

Milestones are the unit of long-running execution. A bad milestone decomposition cascades into days of wasted work. Therefore milestone generation must be adversarial — multiple independent perspectives must challenge each other before milestones are locked.

Hard Gates

1. All 5 reviewer agents must run in parallel. Sequential execution is prohibited. Dispatch all 5 concurrently in a single message via the Agent tool.
2. Each reviewer receives the full problem statement. Do not split or filter the problem per reviewer. Every reviewer sees everything.
3. Reviewers must not see each other's findings. Each reviewer operates independently. No cross-pollination during the review phase.
4. Synthesis must address every reviewer's concern. The synthesis agent must explicitly respond to each finding — accepted, rejected with reason, or deferred to a specific milestone.
5. Every milestone must have measurable success criteria. "Working correctly" is not a criterion. Specific test commands, file existence checks, or behavioral assertions are required.
6. Milestone dependencies must form a DAG. Circular dependencies are a plan failure. Every milestone must have a clear topological ordering.
7. Do not generate milestones for trivial tasks. If the problem can be solved in a single plan-crafting cycle (fewer than ~8 tasks), tell the user to use plan-crafting directly.
8. Reviewer outputs must be passed verbatim to the synthesis agent. Do not summarize, filter, or reframe. Copy each reviewer's full output into the designated placeholder. The main agent must not editorialize the handoff.