model

docs/spec-schema-v2.md

@@ -112,7 +112,7 @@ verification_spec:
 # === REVIEW (before weaver execution) ===
 review_spec:
   type: subagent                 # Spawn reviewer before building
-  model: claude-opus-4-5-20250514  # Review uses Opus 4.5
+  # Uses current session model (Opus 4.5 recommended)
   prompt: |
     Review this spec for quality before building:
     

skills/oracle/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: oracle
 description: Deep planning via Oracle CLI (GPT-5.2 Codex). Use for complex tasks requiring extended thinking (10-60 minutes). Outputs plan.md for planner to transform into specs.
-model: claude-opus-4-5-20250514
 ---
 
 # Oracle

skills/orchestrator/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: orchestrator
 description: Manages weaver execution via tmux. Reads specs, selects skills, launches weavers in parallel, tracks progress. Runs in background.
-model: claude-opus-4-5-20250514
 ---
 
 # Orchestrator

skills/planner/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: planner
 description: Interactive planning agent. Designs verification specs through Q&A with the human. Uses Oracle for complex planning. Hands off to orchestrator for execution.
-model: claude-opus-4-5-20250514
 ---
 
 # Planner

skills/verifier/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: verifier
 description: Verification subagent. Runs checks from verification_spec in order. Fast-fails on first error. Reports PASS or FAIL with evidence. Does NOT modify code.
-model: claude-opus-4-5-20250514
 ---
 
 # Verifier

skills/weaver-base/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: weaver-base
 description: Base skill for all weavers. Implements specs, spawns verifiers, loops until pass, creates PR. Tests are never committed.
-model: claude-opus-4-5-20250514
 ---
 
 # Weaver Base