diff --git a/_assembler/tests/snapshots/code-implementer.snap b/_assembler/tests/snapshots/code-implementer.snap
index 065e701..a82fd29 100644
--- a/_assembler/tests/snapshots/code-implementer.snap
+++ b/_assembler/tests/snapshots/code-implementer.snap
@@ -407,7 +407,7 @@ Blockers / next: <list>
 - Skipping the Pre-Dev Gate on non-trivial work
 - Fixing immediately after Phase 1 of audit without running Phase 2
 - Third attempt with the same failed approach (escalate to Error Budget Level 2 instead)
-- Running `modal app stop` / `pkill` on a running paid job without explicit user confirmation (KILL GUARD applies)
+- Running `modal app stop` / `pkill` on a running paid job without explicit user confirmation (anti-stop guard applies)
 - Rewriting working code without a stated reason (Core Rule 3: Don't Rewrite Working Code)
 - Patching a broken formula with overlay logic instead of fixing it at the root (Core Rule 1: No Patching)
 
diff --git a/_assembler/tests/snapshots/researcher.snap b/_assembler/tests/snapshots/researcher.snap
index 6c47a04..b2b8779 100644
--- a/_assembler/tests/snapshots/researcher.snap
+++ b/_assembler/tests/snapshots/researcher.snap
@@ -187,7 +187,7 @@ Rules: architectural decision → E1-E2. Financial (compute) → ONLY E1. Data >
 
 **Out (hand off):**
 - `validator` — claim needs hard verification (citation sanity, reproduce-in-tests, RULE 0.4 gate before commit)
-- `ml-researcher` — question is ML/RL/CfC-adjacent (Math-First + tooling-reuse + synthetic-to-real discipline)
+- `ml-researcher` — question is ML/RL specialized-node (Math-First + tooling-reuse + synthetic-to-real discipline)
 - `patent-researcher` — question touches patent prior art, FTO, or novelty (IP-aware handling required)
 - `architect` — question is structural/architectural — dependency graph, pattern inventory, module boundaries
 - `critic` — findings suggest anti-pattern sweep or Constructor-Pattern violation review
@@ -195,7 +195,7 @@ Rules: architectural decision → E1-E2. Financial (compute) → ONLY E1. Data >
 # HANDOFFS
 
 - **validator** — claim needs hard verification (citation sanity, reproduce-in-tests, RULE 0.4 gate before commit)
-- **ml-researcher** — question is ML/RL/CfC-adjacent (Math-First + tooling-reuse + synthetic-to-real discipline)
+- **ml-researcher** — question is ML/RL specialized-node (Math-First + tooling-reuse + synthetic-to-real discipline)
 - **patent-researcher** — question touches patent prior art, FTO, or novelty (IP-aware handling required)
 - **architect** — question is structural/architectural — dependency graph, pattern inventory, module boundaries
 - **critic** — findings suggest anti-pattern sweep or Constructor-Pattern violation review