brainstorm.
brainstorm turns a fuzzy “should we build X?” into a justified results document plus a set of concrete, coverage-audited implementation tasks — without writing a line of production code. Its centerpiece is a 6-specialist parallel analysis with a conflict-resolution loop. Every step runs in documentation mode by design.
Steps
- 01Topicread-only
Define the topic in one sentence, why it’s being considered, which modules are affected. Compose the brainstorm task file with its scaffold (Decisions, Expert Analysis, Conflicts).
- 02Discussionread-only
Deep discussion recording every accepted decision. Doubles as the conflict-resolution step — re-entered from analysis when specialists disagree.
OpusAntigravityCodexyour call — answer to go on - 03Analysis6 specialists
The defining step: 6 specialist subagents fan out in a single parallel-dispatch message (plus AI providers when configured). Conflicts loop back to discussion.
6 agents fan out in parallel - 04Resultssynthesize
Synthesize the analysis into a justified results document — the recommendation and its rationale.
- 05Planningdocs only
Turn the results into concrete, coverage-audited implementation tasks, handed off to separate task protocol runs.
writes back to the shared LLM wiki
What makes it distinctive
Six parallel specialists
Analysis launches six specialist subagents in one message — architecture, code-impact, critique, user-perspective, risks & security, scope & phasing — each in its own context window. When AI providers are configured they join in the same parallel dispatch.
Conflict-resolution loop
When specialists disagree, the protocol loops back to discussion: it presents the competing viewpoints, you decide, resolutions are recorded as new decisions, and every open question must be cleared before analysis re-runs.
No production code
The product is knowledge and a plan. Source edits are hook-blocked throughout; the actual build happens in a separate task run.
branch brainstorm/ — b-brainstorm-<name>