Research codebase, validate external claims, and emit a work-ready spec.json for a new planning session. Single-pass creation with integrated validation via Context7 and locator/analyzer agents. Triggers on "create plan", "plan for", "write a plan". For exploratory requests where the user is unsure what to build, prefer brainstorm first. Once spec.json exists, use plan-review for evaluation or go straight to work. For a reviewed spec, use plan-consolidation to merge findings.
Execute spec.json (plan mode) or review.findings.json (fix-findings mode) by dispatching subagents per chunk. Triggers on "work on", "implement", "execute plan", "carry on", "continue".
Shared conventions for Flywheel subagents. Tool discipline, output format, research patterns.
Perform exhaustive code reviews using multi-agent analysis. Reviews PRs, branches, or current changes. Writes review.findings.json to the active session. Triggers on "review", "code review", "check PR".
Refine the active session's spec.json by merging reviewer findings.json into it. Backs up the pre-refinement spec to a .pre-consolidation sidecar. Triggers on "consolidate plan", "finalize plan".
Run ALL reviewer agents in parallel against a plan. Deduplicates findings semantically and writes findings.json to the active session. Triggers on "review plan", "check plan".
Autonomously execute the full plan → implement → review → fix cycle without stopping. The agent makes every decision, including answering open questions during plan-consolidation. Use when you'll be away from the keyboard and trust the agent to ship.
Conversational exploration of ideas before detailed planning. One question at a time, 2-3 approaches, incremental validation. Triggers on "explore", "brainstorm", "think about". Once the approach is clear, use plan-creation to produce a spec.json.