docs(workplans): require task refinement after substantial progress

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a13eab-1e6a-7b33-9c37-372e90ada3a2

scripts/project_rules/session-protocol.template

@@ -56,6 +56,12 @@ For each file with `status: ready`, `active`, or `blocked`, note pending
 
 If no workplans: follow First Session Protocol (`first-session.md`).
 
+**During work:** Refine task structure at substantive checkpoints. Substantial
+completed work must become evidenced completed tasks; split newly understood
+remaining work into owned tasks with completion criteria and real dependencies.
+Keep stable IDs and map moved scope. Progress prose alone is insufficient.
+See workplan-convention.md, “Task refinement after substantial work”.
+
 **During work:** `record_decision()` · `add_progress_event()` · `resolve_decision()`
 
 > State Hub is a *read model*. **Never register workplans or tasks by hand**
@@ -69,7 +75,8 @@ If no workplans: follow First Session Protocol (`first-session.md`).
 > see `workplan-convention.md` (compatibility footnote).
 
 **Session close:**
-1. Update workplan/task statuses in repo files.
+1. Refine task structure after substantial work and update statuses in repo files;
+   record completed deliverables and newly understood remaining tasks before sync.
 2. If marking a workplan **finished**: hand off residuals as **live work
    records** first (intake with `origin: residual` + `origin_ref: <WP-id>`, or
    a child workplan / decision / engagement). Do not leave actionable leftovers