fix(#1505): extract context_guard step to reference file; fix allow-test-rule see ref

- Extract execute-phase.md context_guard step prose to
  gsd-core/references/execute-phase-context-guard.md (@-ref lazy load),
  bringing execute-phase.md back under the ADR-857 phase-6 size ceiling
  (92914 < 93166 bytes)
- Fix allow-test-rule comment: add `see #1452` per ADR-456 lint rule
- Update feat-1452 tests to check the reference file for extracted content
- Register execute-phase-context-guard.md in INVENTORY-MANIFEST.json and
  INVENTORY.md Workflow References section
- Regenerate workflow-size-baseline.json after file shrinkage

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

docs/INVENTORY-MANIFEST.json

@@ -214,6 +214,7 @@
       "edge-probe.md",
       "execute-mvp-tdd.md",
       "execute-phase-between-wave-reset.md",
+      "execute-phase-context-guard.md",
       "execute-phase-wave-guard.md",
       "executor-examples.md",
       "gate-prompts.md",

docs/INVENTORY.md

@@ -301,6 +301,7 @@ Full roster at `gsd-core/references/*.md`. References are shared knowledge docum
 |-----------|------|
 | `agent-contracts.md` | Formal interface between orchestrators and agents. |
 | `context-budget.md` | Context window budget allocation rules. |
+| `execute-phase-context-guard.md` | Context exhaustion guard step for `execute-phase` wave loop — `workflow.context_guard_mode` dispatch table (warn/auto/off) and POOR-tier pause-work trigger (#1452). |
 | `continuation-format.md` | Session continuation/resume format. |
 | `domain-probes.md` | Domain-specific probing questions for discuss-phase. |
 | `edge-probe.md` | Spec-phase edge-completeness probe — 8-category edge taxonomy, shape classification, and the `requirements → checks → verifier` resolution model (Step 5.5). |

gsd-core/references/execute-phase-context-guard.md

@@ -0,0 +1,16 @@
+0. **Context exhaustion guard — `context_guard` (BEFORE spawning, #1452):**
+
+   Before spawning any agents for this wave, self-assess context pressure using the
+   degradation signals in `references/context-budget.md`. Signs of POOR tier (70%+):
+   increasing vagueness, skipped steps, silent partial completion.
+
+   Read `workflow.context_guard_mode` from `.planning/config.json` (default `warn`).
+
+   | Tier | `warn` (default) | `auto` | `off` |
+   |------|-----------------|--------|-------|
+   | PEAK / GOOD | No output | No output | No output |
+   | DEGRADING (50-70%) | Emit: "⚠ Context pressure DEGRADING — switching to frontmatter-only reads for remaining waves." Continue. | Same as warn | Skip |
+   | POOR (70%+) | Emit: "🛑 Context pressure POOR — risk of context exhaustion. Run `/gsd:pause-work` to checkpoint before this wave, then resume in a fresh session." Continue (user decides). | Invoke `/gsd:pause-work` immediately and halt. Do NOT spawn wave agents. | Skip |
+
+   The guard is heuristic — no programmatic context-percentage API exists. Use your
+   assessment of degradation signals, not a fixed token count.

gsd-core/workflows/execute-phase.md

@@ -493,22 +493,7 @@ increases monotonically across waves. `{status}` is `complete` (success),
 
 @~/.claude/gsd-core/references/execute-phase-wave-guard.md
 
-0. **Context exhaustion guard — `context_guard` (BEFORE spawning, #1452):**
-
-   Before spawning any agents for this wave, self-assess context pressure using the
-   degradation signals in `references/context-budget.md`. Signs of POOR tier (70%+):
-   increasing vagueness, skipped steps, silent partial completion.
-
-   Read `workflow.context_guard_mode` from `.planning/config.json` (default `warn`).
-
-   | Tier | `warn` (default) | `auto` | `off` |
-   |------|-----------------|--------|-------|
-   | PEAK / GOOD | No output | No output | No output |
-   | DEGRADING (50-70%) | Emit: "⚠ Context pressure DEGRADING — switching to frontmatter-only reads for remaining waves." Continue. | Same as warn | Skip |
-   | POOR (70%+) | Emit: "🛑 Context pressure POOR — risk of context exhaustion. Run `/gsd:pause-work` to checkpoint before this wave, then resume in a fresh session." Continue (user decides). | Invoke `/gsd:pause-work` immediately and halt. Do NOT spawn wave agents. | Skip |
-
-   The guard is heuristic — no programmatic context-percentage API exists. Use your
-   assessment of degradation signals, not a fixed token count.
+@~/.claude/gsd-core/references/execute-phase-context-guard.md
 
 1. **Intra-wave files_modified overlap check (BEFORE spawning):**
 

tests/feat-1452-context-guard-mode.test.cjs

@@ -1,4 +1,4 @@
-// allow-test-rule: source-text-is-the-product
+// allow-test-rule: source-text-is-the-product see #1452
 // The execute-phase.md workflow and context-budget.md reference ARE the runtime
 // contract loaded by AI runtimes. Asserting that the canonical wording for
 // `workflow.context_guard_mode` is present in those files is the only way to
@@ -126,32 +126,39 @@ describe('workflow.context_guard_mode config round-trip', () => {
 
 describe('execute-phase.md documents the context_guard step', () => {
   let executePhase;
+  let contextGuardRef;
 
   beforeEach(() => {
     executePhase = fs.readFileSync(
       path.join(REPO_ROOT, 'gsd-core', 'workflows', 'execute-phase.md'),
       'utf-8',
     );
+    // The step body is extracted to a reference file loaded via @-ref in execute-phase.md.
+    // Both files together constitute the execute-phase wave-boundary contract.
+    const refPath = path.join(REPO_ROOT, 'gsd-core', 'references', 'execute-phase-context-guard.md');
+    contextGuardRef = fs.existsSync(refPath) ? fs.readFileSync(refPath, 'utf-8') : '';
   });
 
   test('references workflow.context_guard_mode by canonical name', () => {
+    const combined = executePhase + '\n' + contextGuardRef;
     assert.ok(
-      executePhase.includes('workflow.context_guard_mode'),
-      'execute-phase.md must reference workflow.context_guard_mode so runtimes resolve the config-driven behavior',
+      combined.includes('workflow.context_guard_mode'),
+      'execute-phase.md (or its @-referenced execute-phase-context-guard.md) must reference workflow.context_guard_mode so runtimes resolve the config-driven behavior',
     );
   });
 
   test('defines context_guard step at wave boundaries', () => {
     assert.ok(
       executePhase.includes('context_guard') || executePhase.includes('context-guard'),
-      'execute-phase.md must define a context_guard step that fires before each wave',
+      'execute-phase.md must define a context_guard step (or @-ref to it) that fires before each wave',
     );
   });
 
   test('references context-budget.md tiers in the guard step', () => {
+    const combined = executePhase + '\n' + contextGuardRef;
     assert.ok(
-      executePhase.includes('context-budget') || executePhase.includes('POOR') || executePhase.includes('DEGRADING'),
-      'execute-phase.md context_guard must reference context-budget.md degradation tiers',
+      combined.includes('context-budget') || combined.includes('POOR') || combined.includes('DEGRADING'),
+      'execute-phase.md context_guard (or its @-referenced file) must reference context-budget.md degradation tiers',
     );
   });
 });

tests/workflow-size-baseline.json

@@ -24,7 +24,7 @@
   "docs-update.md": 55662,
   "edit-phase.md": 12883,
   "eval-review.md": 9923,
-  "execute-phase.md": 93995,
+  "execute-phase.md": 92914,
   "execute-plan.md": 31365,
   "explore.md": 10497,
   "extract-learnings.md": 12849,