@@ -1306,7 +1306,7 @@ jobs:
       # reader with `check-half-states.mjs`, so the write side and the read-side
       # patrol cannot come to disagree about what a stamp is.
       # Write-pace throttle self-test (#19572) — the shared throttle the four
-      # steps below and `sweep-stale-finding` all issue their writes through,
+      # steps below all issue their writes through,
       # under the maintainer's 「截流应该要加」. Two seat accounts were suspended
       # during bulk issue operations; this file is what makes pacing a property
       # of the write path rather than of who remembered it.
@@ -1458,43 +1458,6 @@ jobs:
         continue-on-error: true
         run: pnpm check:pm-board-snapshot
 
-      # Stale-`finding` sweep self-test (#16904) — same family and the same
-      # split as every step around it, and the split matters more here than for
-      # most: this tool WRITES. Its live path removes a label from real cards on
-      # a shared board, so a production run from CI would relabel the board
-      # because a pull request happened to run — the offline half is the only
-      # half CI can hold, and the sweep itself is run once per board, by hand,
-      # by the seat that owns that board.
-      #
-      # Until this step existed the instrument was UNFIRED: the tool shipped a
-      # 91-case `--self-test` that nothing in CI ran, which is the second half
-      # of the pair `check:self-test-wired` exists for. A script was then IN
-      # that gate's population only once a workflow named it, so the unwired
-      # self-test was a hole only this step could close. Since #21351 the gate
-      # also reads every root `package.json` alias whose expansion carries
-      # `--self-test`, so it holds this step through `check:pm-stale-finding`:
-      # deleting the step reds `[alias-self-test-not-run]`.
-      #
-      # What the self-test instruments is the set of rules a clean tree cannot
-      # exercise: the screen's ungraded verdict, which is the ONE thing the
-      # sweep must never strip (「`finding` ALONE is NOT stale」), the `pm:seat`
-      # refusal, the four-step write's read-back and its refusal on a raced
-      # label set, the batch caps and the resume cursor a 403 leaves, and the
-      # exit register that keeps "could not read the board" apart from "the
-      # board is clean". Weakening any of them leaves an ordinary run just as
-      # green — it would simply strip fewer cards, or more — and a wrong strip
-      # here is a write against a shared board, not a report.
-      #
-      # Since #16904's D2 the screen itself lives in `check-half-states.mjs` and
-      # this tool imports it, so the patrol row that REPORTS the population and
-      # the sweep that STRIPS it read one rule; the patrol's own self-test pins
-      # that this file still aliases that definition rather than re-growing a
-      # copy of it.
-      - name: Stale-`finding` sweep self-test
-        id: stale-finding-sweep-self-test
-        continue-on-error: true
-        run: pnpm check:pm-stale-finding
-
       # Governed-merges audit self-test (#9495) — same family, same split as
       # the half-state sweeper above: the live sweep enumerates the governed
       # merges since a date/ref for the PM round report — report-only by
 
@@ -83,7 +83,6 @@
     "check:issue-citations": "node scripts/check-issue-citations.mjs --self-test",
     "check:pm-record-recognisers": "node scripts/pm/record-recognisers.mjs --self-test && node scripts/pm/check-owed-reviews.mjs --self-test && node scripts/pm/mailbox-open.mjs --self-test && node scripts/pm/fleet-roster.mjs --self-test",
     "check:pm-prior-rulings": "node scripts/pm/check-prior-rulings.mjs --self-test",
-    "check:pm-stale-finding": "node scripts/pm/sweep-stale-finding.mjs --self-test",
     "check:pm-write-pace": "node scripts/pm/write-pace.mjs --self-test",
     "check:pm-fleet-token": "node scripts/pm/fleet-token.mjs --self-test",
     "check:pm-issue-create": "node scripts/pm/issue-create.mjs --self-test",
 
@@ -14966,29 +14966,6 @@ export function h73RuledCardStillInBox(issue, nowMs = Date.now()) {
 // the READ half: the row that makes the refill visible on the patrol instead of
 // being re-measured by whoever next happens to look.
 //
-// ## Why the rule LIVES HERE and the sweep imports it, rather than the reverse
-//
-// `scripts/pm/sweep-stale-finding.mjs` owns the one-time strip and exports this
-// screen. Reusing it BY IMPORT is the ruling, and 「⛔ never a second copy of the
-// rule」 is the reason — but the import can only point one way, and that was
-// measured on this tree rather than assumed:
-//
-//   this file importing the sweep   a MODULE CYCLE that crashes. The sweep
-//                                   derives module-level constants from
-//                                   `PM_STATE_LABELS`, which lives here, so
-//                                   with THIS file as the entry point — every
-//                                   patrol run, every `--self-test` — the
-//                                   sweep's body evaluates first and throws
-//                                   `ReferenceError: Cannot access
-//                                   'PM_STATE_LABELS' before initialization`.
-//   the sweep importing this file   already how it works, for four symbols.
-//
-// So the rule moves DOWN to the module that already owns the vocabulary it is
-// derived from, and the sweep re-exports it under the names its own callers and
-// self-test already use. One source, one arrow, no copy — and the row's
-// population is not an approximation of the sweep's target set, it IS that set,
-// which is what lets the row say "this is what the sweep would strip today".
-//
 // ## The three `pm:*` label sets in this file are NOT this one, and must not be
 //
 // A fourth question, with a fourth answer, stated so nobody unifies it with the
@@ -28123,10 +28100,8 @@ async function selfTest() {
 
   // -- H63 (#16904): a graded card still wearing the ungraded marker ---------
   //
-  // The row over the SHARED screen. Both directions, a lit control under every
-  // silence, and — because the point of sharing the screen is that the row and
-  // the one-time sweep can never disagree — a source-text pin that the sweep
-  // still ALIASES this definition instead of re-growing a copy of it.
+  // The row over the shared screen. Both directions, and a lit control under
+  // every silence.
   const gradedCarrier = (labels, over = {}) => ({
     number: 16904,
     state: 'open',
@@ -28174,19 +28149,6 @@ async function selfTest() {
   t('H63 screen: a priority is a grade in every spelling the board uses', priorityLabelsIn(['priority:p0', 'priority:p3']).length, 2);
   t('H63 screen: ⛔ and priority-ish prose is not a priority label', priorityLabelsIn(['priorities', 'priority', 'prioritypX']).length, 0);
 
-  // ── ONE rule, two readers: the sweep must still ALIAS this definition ─────
-  let sweepSource63 = '';
-  try {
-    sweepSource63 = readFileSync(new URL('./sweep-stale-finding.mjs', import.meta.url), 'utf8');
-  } catch {
-    sweepSource63 = '';
-  }
-  t('H63 ↔ sweep: the sweep\'s source is readable at all (an unreadable one must not pass as clean)', sweepSource63.length > 0, true);
-  t('H63 ↔ sweep: it ALIASES this screen rather than defining one', sweepSource63.includes('export const screenCard = staleFindingScreen;'), true);
-  t('H63 ↔ sweep: …and ⛔ has not re-grown a copy of the screen', /export function screenCard\s*\(/.test(sweepSource63), false);
-  t('H63 ↔ sweep: …nor a second copy of the grading vocabulary', /export const GRADING_STATE_LABELS\s*=/.test(sweepSource63), false);
-  t('H63 ↔ sweep: its target label is this constant, not a second literal', sweepSource63.includes('export const TARGET_LABEL = STALE_FINDING_LABEL;'), true);
-
   // ── ⛔ The three `pm:*` sets stay four different questions ────────────────
   t('H63: H13\'s visibility set carries the marker — which is why H13 is silent on a graded carrier', PM_STATE_LABELS.includes(STALE_FINDING_LABEL), true);
   t('H63 control: …and H13 really is silent on one, because a pm-state is present', h13DomainWithoutPmState({ ...gradedCarrier(['finding', 'pm:queue', 'domain:skills']), updated_at: daysAgo(9) }, NOW), null);
 
@@ -297,15 +297,13 @@ export const ROOT_WALK_RESIDUE_LEDGER = [
   // ⚖️ `check:pm-half-states` LEFT this population under #16904's D2 and its row
   // is gone with it — a listed family that stops being a member reds here, and
   // a stale exclusion is an exclusion nobody measures. It is now placeable BY
-  // PATH, and truthfully: `check-half-states.mjs`'s self-test reads two sibling
-  // sources as program text — `scripts/pm/sweep-stale-finding.mjs` and
-  // `scripts/pm/check-prior-rulings.mjs` — to pin that the sweep still ALIASES
-  // the one stale-`finding` screen rather than re-growing a copy, and that the
-  // prior-ruling line's writer still prints the key the patrol greps. So a card
-  // touching either sibling really does owe this gate, which is the opposite of
-  // the #15753 placement this row was written about: that one came from a
-  // noise-floor constant and said the opposite of what the constant declares,
-  // while these two literals are exactly what the self-test reads.
+  // PATH, and truthfully: `check-half-states.mjs`'s self-test reads a sibling
+  // source as program text — `scripts/pm/check-prior-rulings.mjs` — to pin
+  // that the prior-ruling line's writer still prints the key the patrol greps.
+  // So a card touching that sibling really does owe this gate, which is the
+  // opposite of the #15753 placement this row was written about: that one came
+  // from a noise-floor constant and said the opposite of what the constant
+  // declares, while this literal is exactly what the self-test reads.
   // ⚖️ `scripts/symbol-anchors.mjs --self-test` LEFT this population under
   // #18661 and its row is gone with it — a listed family that stops being a
   // member reds here, and a stale exclusion is an exclusion nobody measures.