Reframe council audit as a one-off backfill, not a standing mode

.claude/skills/council/SKILL.md

@@ -13,18 +13,22 @@ own contract **decides**. When a source conflicts with `SOUL.md`,
 `docs/architecture/10-interaction-and-feedback.md` (interaction contract), **our contract
 wins** — note the divergence and move on.
 
-## Two modes
+## Scope: a steady-state mechanism, with a one-off debt to clear
 
-- **Pointwise (now).** Consult on a single decision in front of you, via the routing table
-  below. Cheap, precise, fits the editing flow — this is the default, and what the
-  auto-triggers fire.
-- **Audit (future).** Periodically sweep the **whole codebase** against the roster — every
-  interactive widget vs. APG, every user-facing string vs. GOV.UK/Carbon content rules,
-  every data surface vs. the loading/empty/error triad, every latency path vs. NN/g budgets
-  — and emit a prioritized gap list into `docs/architecture/10` + `// TODO`s. This is a
-  fan-out review (closer in shape to `/alignment`, but graded against external canon), best
-  run at **milestone boundaries**, not per change — and much of it is milestone-gated anyway
-  (you can't audit modals or datasets that don't exist yet).
+The council's standing job is **pointwise** — consult on the decision in front of you (the
+routing table below), at authoring time. New user-facing work is checked as it's written,
+so it never accrues the drift the council exists to prevent. This is the default, and what
+the auto-triggers fire.
+
+The **backfill** is _not_ a second mode — it's tech debt with an end. Code written _before_
+the council existed was never checked against the roster; reconciling it is a one-off sweep
+(every pre-council widget vs. APG, every user-facing string vs. GOV.UK/Carbon content
+rules, every data surface vs. the loading/empty/error triad), emitting fixes + a gap list
+into `docs/architecture/10`. Done once, **pointwise keeps it honest — there is no recurring
+audit.** The only thing that reopens it is an **event, never a schedule**: seating a new
+member (its principles have never touched existing code) or a source's breaking revision —
+see _Adding a seat_. A light glance at a milestone boundary is a fair safety net for what
+the heuristic auto-trigger missed, but that's the same one-off sweep, not a standing mode.
 
 ## How to convene (the routing rule)
 
@@ -74,6 +78,9 @@ contract, not the external source.
 2. Add one row to **the roster** and one routing entry above.
 3. Keep it lean — a seat earns its place only if it's authoritative for a decision the
    others don't cover well.
+4. **Backfill once.** Reconcile the existing codebase against the new seat — its principles
+   have never been applied before. This is the one event that reopens the one-off sweep
+   (see _Scope_); after it, pointwise maintains the new seat like the rest.
 
 Candidate future seats (not yet seated): **FT Visual Vocabulary / Datawrapper** (chart
 choice — our domain), **Shopify Polaris** (UX-writing depth), **web.dev** (perceived