diff --git a/.opencode/skills/break-glass/SKILL.md b/.opencode/skills/break-glass/SKILL.md
index 5bd38c70..4bc5d0ec 100644
--- a/.opencode/skills/break-glass/SKILL.md
+++ b/.opencode/skills/break-glass/SKILL.md
@@ -5,7 +5,7 @@
 **DO NOT USE THIS SKILL UNLESS ALL OF THE FOLLOWING ARE TRUE:**
 
 1. The user has no solution — they do not know the answer
-2. All free models have been tried and failed
+2. All free models have been tried and failed (including local Gemma4-12B)
 3. All cheap models (< $0.50/call) have been tried and failed
 4. The problem is genuinely novel (not a rehash of known issues)
 5. The problem is blocking progress (not a nice-to-have)
@@ -16,11 +16,21 @@ If the problem is solvable by switching models, just switch models.
 If the problem is solvable by reading docs, just read docs.
 If the problem is solvable by asking the user, just ask the user.
 If a free model can solve it, use the free model.
+If the local Gemma4-12B can solve it, use Gemma4-12B.
 
 **This skill is the last resort before giving up.**
 
 ---
 
+## Primary Model
+
+**Gemma4-12B** (local, free, fast) — use this first for all questions.
+- Endpoint: `http://127.0.0.1:8081/v1`
+- Model ID: `gemma4-12b`
+- API key: `none` (any dummy string)
+- Speed: ~40 tokens/sec generation
+- Strengths: mathematical reasoning, code, Lean 4 proofs
+
 ## Trigger
 
 `break glass: <problem statement>`
@@ -44,10 +54,11 @@ Each model is a dual quaternion (real = compressive, dual = anti-compressive).
 
 ## Escalation
 
-1. **DeepSeek V4 Pro** — try first ($0.27/$1.10)
-2. **Claude Opus** — if DeepSeek stuck ($15/$75)
-3. **GPT-5.5** — if Opus stuck ($10/$30)
-4. **All 8 models** — hard wall ($5-10 total)
+1. **Gemma4-12B** (local, free) — try first
+2. **DeepSeek V4 Pro** — if Gemma stuck ($0.27/$1.10)
+3. **Claude Opus** — if DeepSeek stuck ($15/$75)
+4. **GPT-5.5** — if Opus stuck ($10/$30)
+5. **All 8 models** — hard wall ($5-10 total)
 
 ## Files