Agent definitions: the developer on the smaller model unless the lead says why; review notes

.claude/agents/mesh-developer.md

@@ -2,7 +2,7 @@
 name: mesh-developer
 description: Builds one prepared change of the Novox mesh in local worktrees on a feature branch (hq playbook 07, develop; playbook 08): code and tests, committed locally, never pushed. Starts from the knowledge base and the prepare, and builds only mesh paths.
 tools: Read, Grep, Glob, Bash, Edit, Write, mcp__mesh__mesh_call, mcp__mesh__mesh_describe, mcp__mesh__mesh_search
-model: opus
+model: sonnet
 ---
 
 You build one change of the Novox mesh for the lead who started you. The caller's handover names the issue, the

.claude/agents/mesh-preparer.md

@@ -1,6 +1,6 @@
 ---
 name: mesh-preparer
-description: Prepares one milestone or small fix of the Novox mesh before any code is written (hq playbook 07, the prepare step; playbook 08): what the knowledge base already decides, the mesh path of every interaction the change adds, every file and test it touches, the subtasks and the release order. Read-only.
+description: Prepares one milestone or small fix of the Novox mesh before any code is written (hq playbook 07, the prepare step; playbook 08): what the knowledge base already decides, the mesh path of every interaction the change adds, every file and test it touches, the subtasks and the release order. Read-only but for its prepare file.
 tools: Read, Grep, Glob, Bash, Write, mcp__mesh__mesh_call, mcp__mesh__mesh_describe, mcp__mesh__mesh_search
 model: opus
 ---

.claude/agents/mesh-watcher.md

@@ -15,4 +15,4 @@ line word for word), five minutes passed with no change while something should b
 read and when), the bound passed, or a call failed twice (quote it).
 
 You only read: no verb that writes, never ssh, never a shell helper. Report in a few lines, with times in UTC as
-the tools give them.
+the tools give them; the lead says them to the operator in local time.

00-META/process/07-feature-branches.md

@@ -100,13 +100,15 @@ the running milestone, so the scope above holds. Only an issue in another design
 a time), or one that needs a decision or the operator first, waits, and the report says which and why. Each detailed report's line "Opened along the way" says for every
 issue whether it is being fixed in between, after the delivery, or waits, and on what.
 
-## Step 0 — Prepare (the lead, larger model)
+## Step 0 — Prepare (the lead with mesh-preparer, larger model)
 
 **Agents work from hq's definitions, never from a prompt written by hand.** Every agent the lead starts is one of
 `.claude/agents/`: `mesh-preparer` for this step, `mesh-developer` for step 1, `mesh-code-reviewer` for step 2,
 `mesh-watcher` for every wait, and the four reviewers by architectural domain and `research-reader` of playbook 01.
 The lead writes only the handover: what the agent works on (issue, records, branch, worktrees, commits) and where it
-reports. How it works, what it reads first and what it judges come from its definition; a lesson about how an agent
+reports. How it works, what it reads first and what it judges come from its definition, and so does its model: a
+`mesh-developer` runs on the smaller model, and the lead starts one on the larger model only for work whose parts meet
+at an interface still being designed, written with its reason in the milestone file; a lesson about how an agent
 works goes into its definition by an hq pull request (the operator, 2026-11-03: "please don't write prompts by hand,
 only the handover prompt"). How it is checked: the lead's report names each agent by its definition; an agent started
 from a prompt written by hand is a breach the lead names at the next report.