design
Brainstorming Ideas Into Designs
Overview
All subagent dispatches use disk-mediated dispatch. See shared/dispatch-convention.md for the full protocol.
Turn ideas into fully formed designs through investigated, collaborative dialogue.
Every significant design question is backed by parallel investigation agents that research the codebase, explore approaches, and assess impact BEFORE the question reaches the user. Questions arrive informed, not naive.
Anti-Rationalization Table — design
| Rationalization | Rebuttal | Rule |
|---|---|---|
| "This decision is obvious, I can skip the hypothesis step." | The hypothesis step is a forcing function for noticing surprises — the most valuable output of investigation. Skipping it loses the contrast. | Write the hypothesis before dispatching investigation agents, even when the answer feels obvious. |
| "One investigation agent is enough, I don't need the Challenger." | The Challenger catches assumption blind spots that the recommendation agent inherited. Skipping it is how bad designs ship. | Deep Dive dimensions always dispatch the Challenger (or multi-model consensus challenge when available). |
More from raddue/crucible
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
8adversarial-tester
Use after completing implementation to find unknown failure modes. Reads implementation diff and writes up to 5 tests designed to make it break. Triggers on 'break it', 'adversarial test', 'stress test implementation', 'find weaknesses', or any task seeking to expose unknown failure modes.
5quality-gate
Iterative red-teaming of any artifact (design docs, plans, code, hypotheses, mockups). Loops until clean or stagnation. Invoked by artifact-producing skills or their parent orchestrator.
5code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
5finish
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
4verify
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
4