chore(governance): tighten benchmark fixture gate and decision index

- Raise MIN_TASK_COUNT to 24 and require all nine workflows in validate_benchmark_fixture
- Record Round 68 and post-panel maintenance in PROJECT_KNOWLEDGE Decision Index
- Document benchmark upkeep in CONTRIBUTING, GLOSSARY playbook, and anti-drift tests

Author: johnteee

CONTRIBUTING.md

@@ -31,6 +31,7 @@ Before tuning `route_paraphrase_eval.py`:
 3. When fixing routing boundaries, add holdout phrases **before** editing `route_paraphrase_eval.py` (see `ROUTING_CONTRACT.md` R8–R12).
 4. When cheatsheet cues change, update exported probe tuples in `plans/tests/test_validate_route_fixture.py` and run `test_cheatsheet_*_parity.py` plus `test_cheatsheet_boundary_quick_cues.py`.
 5. Record governance-surface decisions in `PROJECT_KNOWLEDGE.md` Decision Index when routing contract changes.
+6. When adding benchmark golden tasks in `benchmark_tasks.py`, keep all nine workflows covered and update `MIN_TASK_COUNT` in `validate_benchmark_fixture.py`.
 
 See [ROUTING_CONTRACT](reflective-prompt-library/plans/ROUTING_CONTRACT.md) (R8–R12) and the [Governance Maintenance Playbook](reflective-prompt-library/GLOSSARY.md).
 

reflective-prompt-library/GLOSSARY.md

@@ -348,4 +348,5 @@ Ongoing upkeep after panel close (Rounds 1–68). Not agent instructions — ope
 5. Reject tenth skill / full `SKILL.md` i18n unless promotion gate met (panel A, Q, W, AJ).
 6. When cheatsheet boundary quick cues change, update `BOUNDARY_QUICK_CUE_*` markers and probe snippets in `test_validate_route_fixture.py`; run `test_cheatsheet_boundary_quick_cues.py`.
 7. Keep `CONTRIBUTING.md` Routing Maintenance aligned with `ROUTING_CONTRACT.md` R8–R12 when boundaries or cheatsheet parity steps change.
+8. When adding benchmark golden tasks, keep `test_benchmark_covers_all_nine_workflows` green and bump `MIN_TASK_COUNT` in `validate_benchmark_fixture.py` if the floor rises.
 

reflective-prompt-library/PROJECT_KNOWLEDGE.md

@@ -81,6 +81,8 @@ deferred promotions are recurrence-gated — see [panel backlog](plans/multi-age
 - 2026-06-18 Adopt STORM's source-grounded perspective discovery as an optional `reflective-research` method, not a new skill → [record](plans/storm-perspective-discovery-reflection-2026-06-18.md)
 - 2026-06-20 Synthesize external-adoption case studies, then correct the evidence and promotion-gate scope after the Test Plan routing counterexample → [record](plans/external-adoption-case-studies-2026-06-20.md)
 - 2026-06-21 Evaluate Hyperplan / multi-agent adversarial planning — no change (runtime = non-goal; methodology overlaps; possible gaps not promoted) → [record](plans/external-adoption-case-studies-2026-06-20.md)
+- 2026-06-25 Round 68 panel — full-doc drift sync, README/methodology-map anti-drift, reject holdout expansion at 100% → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
+- 2026-06-25 Post-Round 68 maintenance — nine-skill wording parity (METHODOLOGY_MAP, skill-map, QUALITY_GATES), benchmark B024 dispatch (24 tasks, 9/9 workflows) → [QUALITY_GATES_SUMMARY.md](plans/QUALITY_GATES_SUMMARY.md)
 - 2026-06-25 Round 67 panel — CONTRIBUTING R8–R12 sync, ROUTING_CONTRACT related artifacts, contract anti-drift tests → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 66 panel — R12 boundary quick-cue contract, probe-snippet anti-drift, reject quick-cue expansion → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 R11 zh-TW approved-spec delivery holdout — mixed-language ROUTE-003 phrases + router fairness → [ROUTING_CONTRACT.md](plans/ROUTING_CONTRACT.md#r11-approved-spec-delivery)

reflective-prompt-library/plans/tests/test_quality_gates_summary.py

@@ -8,6 +8,7 @@
 
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
+from validate_benchmark_fixture import MIN_TASK_COUNT  # noqa: E402
 from validate_route_fixture import (  # noqa: E402
     ROUTE_001_MIN_PHRASES,
     ROUTE_002_MIN_HOLDOUT_GROUPS,
@@ -110,3 +111,7 @@ def test_benchmark_section_covers_nine_workflows(summary_text: str):
     assert "8 different skills" not in section
     assert "24 golden tasks" in section or "24 benchmark tasks" in section
 
+def test_key_metrics_benchmark_task_count_matches_fixture(summary_text: str):
+    metrics = _section_between(summary_text, "## Key Metrics", "### Routing Consistency Tracking")
+    assert f"| Benchmark tasks | {MIN_TASK_COUNT} |" in metrics
+

reflective-prompt-library/plans/tests/test_validate_benchmark_fixture.py

@@ -31,3 +31,10 @@ def test_benchmark_covers_all_nine_workflows():
         f"unexpected: {sorted(workflows - VALID_WORKFLOWS)}"
     )
 
+def test_benchmark_minimum_matches_actual_count():
+    tasks = BenchmarkSet().tasks
+    assert len(tasks) == MIN_TASK_COUNT, (
+        f"expected MIN_TASK_COUNT {MIN_TASK_COUNT} to match actual {len(tasks)}; "
+        "bump MIN_TASK_COUNT when adding golden tasks"
+    )
+

reflective-prompt-library/plans/validate_benchmark_fixture.py

@@ -23,7 +23,7 @@
 }
 
 VALID_DIFFICULTIES = {"easy", "medium", "hard"}
-MIN_TASK_COUNT = 20
+MIN_TASK_COUNT = 24
 
 
 def main() -> int:
@@ -44,6 +44,14 @@ def main() -> int:
             f"Expected at least {MIN_TASK_COUNT} benchmark tasks; found {len(benchmark.tasks)}"
         )
 
+    workflows = {task.expected_workflow for task in benchmark.tasks}
+    missing_workflows = VALID_WORKFLOWS - workflows
+    if missing_workflows:
+        errors.append(
+            "Benchmark tasks missing workflows: "
+            + ", ".join(sorted(missing_workflows))
+        )
+
     seen_ids = set()
     for task in benchmark.tasks:
         if not task.id: