Merge origin/main (v1.57.4.0) into garrytan/upgrade-gbrain-use

Resolves VERSION/CHANGELOG/package.json (branch keeps v1.57.5.0; my entry on top,
main's v1.57.4.0 Boil-the-Ocean rename entry below). Regenerated SKILL.md across
hosts (picks up the Boil-the-Lake to Boil-the-Ocean rename). Bumped plan-eng-review
maxSizeRatio to 1.06 for the cumulative cross-cutting preamble growth.

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

test/fixtures/golden/claude-ship-SKILL.md

@@ -167,7 +167,7 @@ touch ~/.gstack/.writing-style-prompted
 
 Skip if `WRITING_STYLE_PENDING` is `no`.
 
-If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Lake** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
+If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
 
 ```bash
 open https://garryslist.org/posts/boil-the-ocean
@@ -622,9 +622,9 @@ Applies to AskUserQuestion, user replies, and findings. AskUserQuestion Format i
 Curated jargon list lives at `~/.claude/skills/gstack/scripts/jargon-list.json` (80+ terms). On the first jargon term you encounter this session, Read that file once; treat the `terms` array as the canonical list. The list is repo-owned and may grow between releases.
 
 
-## Completeness Principle — Boil the Lake
+## Completeness Principle — Boil the Ocean
 
-AI makes completeness cheap. Recommend complete lakes (tests, edge cases, error paths); flag oceans (rewrites, multi-quarter migrations).
+AI makes completeness cheap, so the complete thing is the goal. Recommend full coverage (tests, edge cases, error paths) — boil the ocean one lake at a time. The only thing out of scope is genuinely unrelated work (rewrites, multi-quarter migrations); flag that as separate scope, never as an excuse for a shortcut.
 
 When options differ in coverage, include `Completeness: X/10` (10 = all edge cases, 7 = happy path, 3 = shortcut). When options differ in kind, write: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate scores.
 

test/fixtures/golden/codex-ship-SKILL.md

@@ -153,7 +153,7 @@ touch ~/.gstack/.writing-style-prompted
 
 Skip if `WRITING_STYLE_PENDING` is `no`.
 
-If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Lake** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
+If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
 
 ```bash
 open https://garryslist.org/posts/boil-the-ocean
@@ -608,9 +608,9 @@ Applies to AskUserQuestion, user replies, and findings. AskUserQuestion Format i
 Curated jargon list lives at `$GSTACK_ROOT/scripts/jargon-list.json` (80+ terms). On the first jargon term you encounter this session, Read that file once; treat the `terms` array as the canonical list. The list is repo-owned and may grow between releases.
 
 
-## Completeness Principle — Boil the Lake
+## Completeness Principle — Boil the Ocean
 
-AI makes completeness cheap. Recommend complete lakes (tests, edge cases, error paths); flag oceans (rewrites, multi-quarter migrations).
+AI makes completeness cheap, so the complete thing is the goal. Recommend full coverage (tests, edge cases, error paths) — boil the ocean one lake at a time. The only thing out of scope is genuinely unrelated work (rewrites, multi-quarter migrations); flag that as separate scope, never as an excuse for a shortcut.
 
 When options differ in coverage, include `Completeness: X/10` (10 = all edge cases, 7 = happy path, 3 = shortcut). When options differ in kind, write: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate scores.
 

test/fixtures/golden/factory-ship-SKILL.md

@@ -155,7 +155,7 @@ touch ~/.gstack/.writing-style-prompted
 
 Skip if `WRITING_STYLE_PENDING` is `no`.
 
-If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Lake** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
+If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
 
 ```bash
 open https://garryslist.org/posts/boil-the-ocean
@@ -610,9 +610,9 @@ Applies to AskUserQuestion, user replies, and findings. AskUserQuestion Format i
 Curated jargon list lives at `$GSTACK_ROOT/scripts/jargon-list.json` (80+ terms). On the first jargon term you encounter this session, Read that file once; treat the `terms` array as the canonical list. The list is repo-owned and may grow between releases.
 
 
-## Completeness Principle — Boil the Lake
+## Completeness Principle — Boil the Ocean
 
-AI makes completeness cheap. Recommend complete lakes (tests, edge cases, error paths); flag oceans (rewrites, multi-quarter migrations).
+AI makes completeness cheap, so the complete thing is the goal. Recommend full coverage (tests, edge cases, error paths) — boil the ocean one lake at a time. The only thing out of scope is genuinely unrelated work (rewrites, multi-quarter migrations); flag that as separate scope, never as an excuse for a shortcut.
 
 When options differ in coverage, include `Completeness: X/10` (10 = all edge cases, 7 = happy path, 3 = shortcut). When options differ in kind, write: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate scores.
 

test/helpers/carve-guards.ts

@@ -161,6 +161,10 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     maxSkeletonBytes: 62_000,
     minUnionBytes: 70_000,
     mustContain: ['Architecture', 'Code Quality', 'Test', 'Performance'],
+    // Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback + the
+    // decision-memory nudge + the v1.57.4.0 Boil-the-Ocean rename) lands this just
+    // over the strict 1.05; small headroom for the shared preamble additions.
+    maxSizeRatio: 1.06,
   },
   'plan-design-review': {
     skill: 'plan-design-review',

test/skill-validation.test.ts

@@ -837,7 +837,7 @@ describe('Completeness Principle in generated SKILL.md files', () => {
     test(`${skill} contains Completeness Principle section`, () => {
       const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
       expect(content).toContain('Completeness Principle');
-      expect(content).toContain('Boil the Lake');
+      expect(content).toContain('Boil the Ocean');
     });
   }
 

test/terse-build.test.ts

@@ -64,10 +64,10 @@ describe('terse build — per-resolver behavior', () => {
   });
 
   describe('generateCompletenessSection', () => {
-    test('default: emits full section with Boil-the-Lake prose', () => {
+    test('default: emits full section with Boil-the-Ocean prose', () => {
       const out = generateCompletenessSection(makeCtx('default'));
       expect(out).toContain('## Completeness Principle');
-      expect(out).toContain('Boil the Lake');
+      expect(out).toContain('Boil the Ocean');
     });
 
     test('terse: returns empty string', () => {