Frame-Problem to Brainstorm Handoff

Thinking Trail

• Considered: {what approaches were weighed during framing}
• Rejected: {why other domains didn't fit — prevents brainstorm re-exploring}
• Surprised by: {unexpected signals in the problem statement}
• Triangulation: T1={Keogh level}, T2={predictability}, T3={disassembly} — {convergence}
• Models used: Cynefin triangulation (Keogh + Predictability + Disassembly)
• Constraints discovered: {enabling constraints identified — cause-effect unclear}

Decisions

1. Domain: Complex (enabling constraints — experimentation needed)
2. Route: brainstorm → probe → openspec-plan
3. Rationale: {why divergent exploration before probing}

Actions Taken

• Classified via Q1: enabling constraints identified
• Scale determined: {boulder|pebble}

Output

🎯 Complex → Probe → /brainstorm → /probe | OpenSpec: yes | Scale: {scale}

Domain Transition

From: Confused → To: Complex Constraint shift: unknown → enabling. Problem has no clear cause-effect; need divergent exploration to surface hypotheses before probing.

For /brainstorm

• Goal: Generate 3-5 hypotheses about what's happening and why
• Constraint: Each hypothesis must be falsifiable — probe needs testable claims
• Output format: Ranked hypotheses with confidence levels and suggested probe approaches
• Do NOT: Converge to a solution — brainstorm feeds probe, not implementation

Accumulated Context

Token guidance: target 300 tokens inline. For depth, use references — point to thinking artifact files rather than embedding full content. Soft cap: 600 tokens inline per handoff. If you need more, move detail to a knowledge file and reference it. Accumulated cap: 800 tokens across a chain — compress to 200 at cap (keep: decisions, constraints, rejected paths). References to thinking files do NOT count toward the cap.