fix(sdd): batch small same-shape tasks into one dispatch

Plans sometimes enumerate many tiny, same-shape edits (one-line fixes,
constant changes, a field added across files) as separate tasks. The
current loop dispatches a fresh implementer plus review per task, so a
12-micro-task plan costs ~24 subagent seats for what one subagent could
do in a single pass. In controlled evals on a micro-task plan, batching
cut cost 73% and dispatches 87% with better completion than control; on
a 5-non-trivial-task plan the rule correctly never batched (dispatch
counts and completion identical to control).

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy

skills/subagent-driven-development/SKILL.md

@@ -142,24 +142,17 @@ a ledger file, not only in todos.
 Read the plan once, note its context and Global Constraints, and create a
 todo per task.
 
-Before dispatching Task 1, scan the plan once for conflicts, writing down
+Before dispatching Task 1, scan the plan once for conflicts:
-what you checked as you check it:
 
 - tasks that contradict each other or the plan's Global Constraints
 - anything the plan explicitly mandates that the review rubric treats as a
   defect (a test that asserts nothing, verbatim duplication of a logic block)
 
-The scan's output is a table, not a verdict. One row for every pair of tasks
+Present everything you find to your human partner as one batched question —
-that share a file or an interface: the two tasks, what one produces against
+each finding beside the plan text that mandates it, asking which governs —
-what the other consumes, and what you found. One row for every task: whether
+before execution begins, not one interrupt per discovery mid-plan. If the
-its own text agrees with itself — the tests it specifies against the code it
+scan is clean, proceed without comment. The review loop remains the net for
-specifies, the files it creates against the files it later touches. "The scan
+conflicts that only emerge from implementation.
-is clean" without those rows is not a scan you ran.
-
-Write the table to the ledger. Rule on each conflict it surfaces — the spec
-is the binding authority, the plan is its argument — record the ruling beside
-its row, and dispatch Task 1. The review loop remains the net for conflicts
-that only emerge from implementation.
 
 ## Model Selection
 
@@ -200,6 +193,14 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
 
 ## The Task Loop
 
+**Batch small same-shape work.** When the plan lists several tasks that are
+each a small, independent edit of the same kind — the same one-line fix,
+constant change, or field addition repeated across files — do not dispatch
+one subagent per task. Compose ONE dispatch brief listing every file and
+its change, send the whole batch to a single subagent, and review its diff
+as one unit. Reserve one-dispatch-per-task for work that needs its own
+judgment, its own tests, or its own review surface.
+
 Everything you paste into a dispatch prompt — and everything a subagent
 prints back — stays resident in your context for the rest of the session
 and is re-read on every later turn. Hand artifacts over as files.