feat(skl,cml): --context-window calibration, advisory when unknown (v5.11 B8) [skip-docs]

SKL-002 (skill-listing budget) and CML char-budget now calibrate to a
resolved context window instead of always anchoring at 200k:

- resolveContextWindow(): --context-window <n> calibrates; 'auto' keeps the
  conservative 200k anchor but marks advisory (model→window probing deferred
  to B8b); no flag → 200k anchor, byte-identical to pre-B8 default.
- scaleForWindow(): linear off the 200k anchor (identity at the anchor).
- SKL + CML each keep an untouched default branch (window===200k && !advisory)
  for byte-stability and a calibrated branch; advisory downgrades the budget
  finding from a breach (low/medium) to info.
- Flag wired through scan-orchestrator + posture; runAllScanners resolves once
  and threads { contextWindow } to scanners (others ignore the 3rd arg).
- CPS intentionally excluded: it has no window-anchored budget (fixed
  150-line volatility heuristic), so there is nothing to calibrate.

15 new tests; e2e CLI verified (1M suppresses SKL-002, auto → info, default
unchanged); full suite 1279 green; snapshots byte-stable.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/scanners/claude-md-linter.test.mjs

@@ -172,6 +172,38 @@ describe('CML scanner — char budget mirrors CC startup warning (CC 2.1.169)',
   });
 });
 
+describe('CML scanner — context-window calibration (B8)', () => {
+  const FIXTURE = resolve(FIXTURES, 'large-claude-chars'); // 48,531 chars
+  const charFinding = (r) =>
+    r.findings.find((f) => /performance-warning threshold/i.test(f.title || ''));
+
+  async function scanWithCtx(contextWindow) {
+    resetCounter();
+    const discovery = await discoverConfigFiles(FIXTURE);
+    return scan(FIXTURE, discovery, { contextWindow });
+  }
+
+  it('--context-window 1000000 relaxes the 40k char threshold so a 48k-char file does NOT fire', async () => {
+    const at1m = await scanWithCtx({ window: 1_000_000, advisory: false });
+    assert.equal(charFinding(at1m), undefined,
+      '48,531 chars is under the ~200,000-char threshold at a 1M window');
+  });
+
+  it('an unknown (advisory) window keeps the 40k anchor but downgrades to info', async () => {
+    const advisory = await scanWithCtx({ window: 200_000, advisory: true });
+    const f = charFinding(advisory);
+    assert.ok(f, 'still surfaces the measurement at the conservative anchor');
+    assert.equal(f.severity, 'info', 'advisory downgrades it from medium to info');
+  });
+
+  it('no opts (default) is unchanged: fires medium at the 40k anchor', async () => {
+    resetCounter();
+    const discovery = await discoverConfigFiles(FIXTURE);
+    const result = await scan(FIXTURE, discovery);
+    assert.equal(charFinding(result)?.severity, 'medium', 'default must stay byte-stable: medium');
+  });
+});
+
 describe('CML scanner — large-by-lines but under the char budget (no false char finding)', () => {
   // large-cascade/CLAUDE.md is 1024 lines but only 37,393 chars (short lines):
   // under CC's 40.0k char threshold, so the char-budget finding must NOT fire —