feat(agent): break-glass as fusion of fusions (16D model)

4 dimensions × 2 models each, structured like 16D braid:
- Math: DeepSeek V4 Pro + Gemini 3.1 Pro
- Proof: Claude Opus + Cohere Command A+
- Code: GPT-5.5 + Kimi K2.6
- Diversity: GLM-5.2 + DeepSeek V4 Flash

Each dimension fuses independently, then results fuse together.
Maps to OpenRouter Fusion with 8-model panel.

Cost: -10 for full fusion, /usr/bin/bash.10-2 for single dimension.

.opencode/skills/break-glass/SKILL.md

@@ -4,27 +4,61 @@
 
 `break glass: <problem statement>`
 
-## What It Does
+## Architecture: Fusion of Fusions
 
-Tells you which model to switch to. OpenCode handles the routing.
+4 dimensions × 2 models each = 8 models, structured like 16D braid.
+Each dimension tackles a different aspect. Dimensions fuse independently,
+then results fuse together.
 
-## Model Selection Card
+```
+Dim 1: Math      ─── DeepSeek V4 Pro + Gemini 3.1 Pro ───┐
+Dim 2: Proof     ─── Claude Opus + Cohere Command A+  ───┤
+Dim 3: Code      ─── GPT-5.5 + Kimi K2.6             ───┼── Fusion
+Dim 4: Diversity ─── GLM-5.2 + DeepSeek V4 Flash      ───┘
+```
 
-| Model | $/1M in | $/1M out | Best For |
-|-------|---------|----------|----------|
-| DeepSeek V4 Flash | $0.07 | $0.28 | Quick checks |
-| DeepSeek V4 Pro | $0.27 | $1.10 | Math, code (default) |
-| Gemini 3 Flash | $0.075 | $0.30 | Budget diversity |
-| Gemini 3.1 Pro | $1.25 | $5.00 | Different perspective |
-| Kimi K2.6 | $0.50 | $2.00 | Code |
-| Cohere Command A+ | $2.50 | $10.00 | Structured output |
-| GLM-5.2 | $1.00 | $4.00 | Different architecture |
-| GPT-5.5 | $10.00 | $30.00 | Breadth, ops |
-| Claude Opus 4.8 | $15.00 | $75.00 | Formal proof, synthesis |
+## Dimensions
+
+| Dim | Models | $/1M (in/out) | Tackles |
+|-----|--------|---------------|---------|
+| **Math** | DeepSeek V4 Pro + Gemini 3.1 Pro | $0.27/$1.10 + $1.25/$5 | Reasoning, proofs, formulas |
+| **Proof** | Claude Opus + Cohere Command A+ | $15/$75 + $2.50/$10 | Formal verification, Lean, structured output |
+| **Code** | GPT-5.5 + Kimi K2.6 | $10/$30 + $0.50/$2 | Implementation, debugging, tool use |
+| **Diversity** | GLM-5.2 + DeepSeek V4 Flash | $1/$4 + $0.07/$0.28 | Different architecture, fast iteration |
+
+## Cost
+
+| Mode | Models | Cost |
+|------|--------|------|
+| **Single dim** | 2 models | $0.10-$2.00 |
+| **Two dims** | 4 models | $0.50-$5.00 |
+| **Full fusion** | 8 models | $1.00-$10.00 |
+
+## OpenRouter Fusion Call
+
+```json
+{
+  "model": "openrouter/fusion",
+  "plugins": [{
+    "id": "fusion",
+    "model": "deepseek/deepseek-v4-pro",
+    "analysis_models": [
+      "deepseek/deepseek-v4-pro",
+      "google/gemini-3.1-pro-preview",
+      "anthropic/claude-opus-4.8",
+      "cohere/command-a-03-2026",
+      "openai/gpt-5.5",
+      "moonshotai/kimi-k2.6",
+      "zhipu/glm-5.2",
+      "deepseek/deepseek-v4-flash"
+    ]
+  }]
+}
+```
 
 ## Escalation
 
-1. **DeepSeek V4 Pro** — try first ($0.27/$1.10, 55x cheaper than Opus)
-2. **Claude Opus** — if DeepSeek stuck ($15/$75)
-3. **GPT-5.5** — if Opus stuck ($10/$30)
-4. **All 8** — hard wall ($5-10 total)
+1. **Single dim** (Math) — try first, cheapest
+2. **Two dims** (Math + Proof) — if stuck
+3. **Full fusion** (all 4 dims) — hard wall
+4. **Full fusion + recursive** — break glass (call Fusion, read result, call again)