E27 stack: conditional impl tier + final-review tier pin + narration recipe + terse reviewer contract

skills/subagent-driven-development/SKILL.md

@@ -11,6 +11,9 @@ Execute plan by dispatching a fresh implementer subagent per task, a task review
 
 **Core principle:** Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration
 
+**Narration:** between tool calls, narrate at most one short line — the
+ledger and the tool results carry the record.
+
 **Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
 
 ## When to Use
@@ -88,6 +91,8 @@ Use the least powerful model that can handle each role to conserve cost and incr
 **Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
 
 **Architecture and design tasks**: use the most capable available model.
+The final whole-branch review is one of these — dispatch it on the most
+capable available model, not the session default.
 
 **Review tasks**: choose the model with the same judgment, scaled to the
 diff's size, complexity, and risk. A small mechanical diff does not need the
@@ -100,8 +105,10 @@ most expensive — which silently defeats this section.
 **Turn count beats token price.** Wall-clock and context cost scale with how
 many turns a subagent takes, and the cheapest models routinely take 2-3× the
 turns on multi-step work — costing more overall. Use a mid-tier model as the
-floor for implementers and reviewers; reserve the cheapest tier for
-single-file mechanical fixes.
+floor for reviewers and for implementers working from prose descriptions.
+When the task's plan text contains the complete code to write, the
+implementation is transcription plus testing: use the cheapest tier for
+that implementer. Single-file mechanical fixes also take the cheapest tier.
 
 **Task complexity signals (implementation tasks):**
 - Touches 1-2 files with a complete spec → cheap model

skills/subagent-driven-development/task-reviewer-prompt.md

@@ -115,6 +115,11 @@ Subagent (general-purpose):
     "yes." A tight report that cites lines gives the controller everything
     it needs.
 
+    Your final message is the report itself: begin directly with the
+    spec-compliance verdict. Every line is a verdict, a finding with
+    file:line, or a check you ran — no preamble, no process narration,
+    no closing summary.
+
     ## Calibration
 
     Categorize issues by actual severity. Not everything is Critical.