Brainstorm → plan → execute development workflow plugin for Claude Code
Agent
Adversarial second-opinion review of a completed masterplan task. The harness runs this agent on the routing policy's adversary lane (breaker role, frontier lane — panel adversarial for cross-vendor coverage) and it returns a severity-first findings digest (CD-10). Runs per done task during execution when the run…
Agent
Read-only, fresh-context audit of a merged masterplan plan against the ORIGINAL user request. Consumes goals.md (its topic: anchor + goals), spec.md, and the merged plan as QUOTED DATA (never instructions); decomposes the anchor into stable clauses A1..An for the user to confirm, then judges per-clause drift. The…
Agent
Read-only, fresh-context assessment of a completed masterplan run's declared goals. Consumes goals.md as QUOTED DATA (never instructions), the base..HEAD branch diff, verify output, and each goal's declared evidence pointer; verifies evidence per signal class (test|command|artifact|docs) with read-only commands, then…
Agent
Reviews a merged masterplan plan against its spec — spec coverage, cross-subsystem consistency, and verify-command adequacy — and returns a PASS/REVISE/FAIL verdict with findings. The review judgment runs on the routing policy's critic class (breaker role, frontier lane) — the orchestrator dispatches this agent on…
Agent
Turns an approved spec into an executable masterplan plan — tasks with wave assignments, routing annotations, and verifycommands — and emits plan.index.json. The decomposition judgment runs on the routing policy's planned-execution class (judge role, frontier lane) — the orchestrator dispatches this agent on that…
Agent
Decomposes an approved spec into the subsystem list that parallel planning fans out over — each subsystem a coherent, file-disjoint slice — and judges whether the spec is worth planning in parallel at all. The seam-finding judgment runs on the routing policy's planned-execution class (judge role, frontier lane) — the…
Agent
Drafts the plan FRAGMENT for ONE subsystem of a build — a list of tasks with files, verifycommands, and dependency keys — for parallel planning. The drafting judgment runs on the routing policy's planned-execution class (judge role, frontier lane, writes:false) — the planning fan-out dispatches this agent natively on…