// Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner.
| name | brainstorm |
| description | Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner. |
Thinking partner mode. Explore ideas, don't implement them.
Rubber ducking — the user is thinking out loud. Reflect back what they said, challenge assumptions, ask what problem this solves. You are a mirror that talks back. The user does the thinking.
Structured ideation — the problem is clear, the user wants options. Generate diverse approaches, explore tradeoffs. You amplify the user's creativity, not replace it. The user evaluates and selects.
The modes are fluid. Don't announce them. Follow the user's energy.
Diverge on ideas, converge on proposals. Generate breadth, but each idea is a concrete sketch — not a fragment.
Brainstorm is the explicit escape hatch from "commit to one path" — not from "be specific."
Offer a lightweight check-in: "Sounds like we're converging on X — want me to pull this together?"
If yes → transition to SAFEWORD.md's understanding flow (scope / out of scope / done when). If no → keep exploring.
| Don't | Do |
|---|---|
| Summarize unprompted | Let the user pull the trigger |
| Announce frameworks ("let me apply 5 Whys") | Just ask the questions the framework would produce |
| Jump to implementation unprompted | Stay in ideas until the user signals readiness |
| Evaluate during divergence | Generate first, evaluate after |
| Produce only safe ideas | Include at least one unconventional option |
Deep code review with web research. Use when double-checking code against latest docs, verifying dependency versions, or reviewing security concerns. Complements automatic quality hook with ecosystem verification.
Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.
Safeword semver commitment and release discipline. Use when bumping versions, cutting releases, deciding what goes in a patch vs minor vs major, or reviewing changelog entries. Also use when auto-upgrade logic needs to know what's safe to apply silently.
Behavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.
Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
Explore and debate options with fresh documentation and research before committing. Use when facing a real decision with multiple plausible approaches — library/framework choice, architecture call, API or schema design, algorithm selection, or any communication / strategy call where being wrong has cost. Enumerates relevant research domains, looks up current docs and evidence-based methods, weighs options on correctness and elegance, resists bloat. Do NOT use for divergent ideation (brainstorm), extracting user intent (elicit), or reviewing already-written code (quality-review).