Make subagent optimizer deterministic

Co-authored-by: mnkiefer <8320933+mnkiefer@users.noreply.github.com>

Author: Copilot

.github/workflows/daily-subagent-optimizer.lock.yml

@@ -3,7 +3,7 @@ name: Daily Sub-Agent Optimizer
 description: Identifies high-token workflows lacking inline sub-agents, applies LLM-expert heuristics to locate decomposable tasks, and creates a concrete inline-agent refactoring proposal
 on:
   schedule:
-    - cron: daily
+    - cron: "35 3 * * *"
   workflow_dispatch:
 permissions:
   contents: read
@@ -36,8 +36,6 @@ safe-outputs:
 timeout-minutes: 30
 ---
 
-{{#runtime-import? .github/shared-instructions.md}}
-
 # Daily Sub-Agent Optimizer
 
 You are an LLM efficiency expert specializing in agentic workflow optimization. Your mission today: identify one workflow that would benefit from inline sub-agent refactoring, reason carefully about which tasks a smaller model (small alias) can handle, and produce a copy-paste-ready proposal issue.

.github/workflows/daily-subagent-optimizer.md

@@ -3,7 +3,7 @@ name: Daily Sub-Agent Optimizer
 description: Identifies high-token workflows lacking inline sub-agents, applies LLM-expert heuristics to locate decomposable tasks, and creates a concrete inline-agent refactoring proposal
 on:
   schedule:
-    - cron: daily
+    - cron: "35 3 * * *"
   workflow_dispatch:
 permissions:
   contents: read
@@ -36,8 +36,6 @@ safe-outputs:
 timeout-minutes: 30
 ---
 
-{{#runtime-import? .github/shared-instructions.md}}
-
 # Daily Sub-Agent Optimizer
 
 You are an LLM efficiency expert specializing in agentic workflow optimization. Your mission today: identify one workflow that would benefit from inline sub-agent refactoring, reason carefully about which tasks a smaller model (small alias) can handle, and produce a copy-paste-ready proposal issue.