docs(governance): Round 67 panel — contributor doc parity for R8–R12

Author: johnteee

CONTRIBUTING.md

@@ -28,10 +28,11 @@ Before tuning `route_paraphrase_eval.py`:
 
 1. Add fresh holdout phrases to `route-002-holdout-eval.yaml` and/or adversarial cases to `route-003-adversarial-eval.yaml`.
 2. Run `make all` — `validate_route_fixture.py` enforces minimum fixture coverage.
-3. When fixing review-vs-risk or plan-only boundaries, add holdout phrases **before** editing `route_paraphrase_eval.py` (see `ROUTING_CONTRACT.md` R8–R9).
-3. Record governance-surface decisions in `PROJECT_KNOWLEDGE.md` Decision Index when routing contract changes.
+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.
 
-See [ROUTING_CONTRACT R8](reflective-prompt-library/plans/ROUTING_CONTRACT.md) and the [Governance Maintenance Playbook](reflective-prompt-library/GLOSSARY.md).
+See [ROUTING_CONTRACT](reflective-prompt-library/plans/ROUTING_CONTRACT.md) (R8–R12) and the [Governance Maintenance Playbook](reflective-prompt-library/GLOSSARY.md).
 
 ## Quality Standards
 

reflective-prompt-library/GLOSSARY.md

@@ -337,7 +337,7 @@ Curated top-of-cheatsheet summary of high-confusion routing traps (ROUTE-002 hol
 
 ## Governance Maintenance Playbook / 治理維護手冊
 
-Ongoing upkeep after panel close (Rounds 1–66). Not agent instructions — operator checklist.
+Ongoing upkeep after panel close (Rounds 1–67). Not agent instructions — operator checklist.
 
 **Operational test:** Before router tuning, add fresh ROUTE-002/003 holdout phrases; run `make validate`; record decisions in `PROJECT_KNOWLEDGE.md` Decision Index when governance surface changes.
 
@@ -347,4 +347,5 @@ Ongoing upkeep after panel close (Rounds 1–66). Not agent instructions — ope
 4. Keep manual `benchmark_tasks.py` runs optional — fixture gate only in CI.
 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.
 

reflective-prompt-library/PROJECT_KNOWLEDGE.md

@@ -41,7 +41,7 @@ operating its own agent runtime. See [README.md](README.md#north-star).
 > does not silently expand. Completed milestones are retired from this section;
 > their outcomes live in the Decision Index.
 
-**Ongoing (post Round 66 panel):** maintain ROUTE-001/002/003 evals, governance validators,
+**Ongoing (post Round 67 panel):** maintain ROUTE-001/002/003 evals, governance validators,
 and holdout expansion before router tuning — see [GLOSSARY.md](GLOSSARY.md) Governance
 Maintenance Playbook. Post-panel maintenance (e.g. ROUTING_CONTRACT R11 approved-spec delivery)
 follows the same holdout-before-tune rule. No open implementation blockers from Rounds 8–20;
@@ -81,6 +81,7 @@ 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 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)
 - 2026-06-25 R11 approved-spec delivery routing — `implement_not_plan_trap` fix, ROUTE-003 back to 100%, contract + anti-drift test → [ROUTING_CONTRACT.md](plans/ROUTING_CONTRACT.md#r11-approved-spec-delivery)

reflective-prompt-library/plans/ROUTING_CONTRACT.md

@@ -147,5 +147,7 @@ Next Action:
 
 - `plans/code-followups-plan.md` (`ROUTE-001`)
 - `plans/route-001-paraphrase-eval.yaml`
+- `plans/route-002-holdout-eval.yaml`, `plans/route-003-adversarial-eval.yaml`
 - `skills/reflective-dispatch/SKILL.md`
-- `skills/SKILL_TRIGGER_CHEATSHEET.md`
+- `skills/SKILL_TRIGGER_CHEATSHEET.md`, `skills/SKILL_TRIGGER_CHEATSHEET.zh-TW.md`
+- `plans/tests/test_cheatsheet_boundary_quick_cues.py`, `plans/tests/test_cheatsheet_*_parity.py`

reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md

@@ -1262,8 +1262,102 @@ User directive: **do anything you want** — reopen panel for post-`cb6ea2b` bou
 
 - `make all`: pytest + ROUTE-001/002/003 100%
 
+
+
+## Round 67 — Contributor doc parity (2026-06-25)
+
+User directive: **do anything you want** — reopen panel for post-Round-66 operator/contributor doc drift.
+
+### CM: CONTRIBUTING Routing Maintenance sync (R8–R12)?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Agree** — duplicate step 3 and stale R8–R9 pointer are governance drift |
+| Codex | **Agree** — cheatsheet parity belongs in contributor path, not only playbook |
+| Gemini | **Agree** — fix numbering before adding steps |
+| Composer | **Agree** — IDE contributors read CONTRIBUTING first |
+| Sakana | **Agree** — no new skill; doc alignment only |
+| GLM | **Agree** — zh-TW cheatsheet parity step explicit |
+
+**Socratic Q:** Does CONTRIBUTING duplicate GLOSSARY playbook?
+**Answer:** CONTRIBUTING is the fork/PR entry point; playbook stays operator-deep. Cross-link only.
+
+**Consensus:** **Agree** — fix duplicate step 3; extend to R8–R12; add cheatsheet parity step.
+
+### CN: ROUTING_CONTRACT Related Artifacts expansion?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Agree** — holdout YAMLs, zh-TW cheatsheet, parity pytest files |
+
+**Consensus:** **Agree**.
+
+### CO: `test_routing_contract.py` anti-drift?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Agree** — R8–R12 presence is falsifiable |
+| Codex | **Agree** — mirrors `test_quality_gates_summary.py` pattern |
+| Gemini | **Agree** — Related Artifacts drift is recurring |
+| Composer | **Agree** — low-cost CI guard |
+| Sakana | **Agree** — contract structure, not router logic |
+| GLM | **Agree** — includes zh-TW cheatsheet artifact |
+
+**Consensus:** **Agree** — structural pytest for R8–R12 + related artifacts.
+
+### CP: Expand ROUTE holdout or tune router?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Reject** — ROUTE-001/002/003 at 100%; no new boundary evidence |
+
+**Consensus:** **Reject** — maintenance only.
+
+### CQ: GLOSSARY playbook step 7 (CONTRIBUTING alignment)?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Agree** — step 7 when R8–R12 or cheatsheet steps change |
+
+**Consensus:** **Agree**.
+
+### CR: Re-litigate backlog?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Unchanged** — recurrence-gated backlog stands |
+
+**Consensus:** **Agree** — no backlog changes.
+
+### Round 67 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| CM | CONTRIBUTING R8–R12 sync | **Agree** | `CONTRIBUTING.md` |
+| CN | Related Artifacts expansion | **Agree** | `ROUTING_CONTRACT.md` |
+| CO | Contract anti-drift pytest | **Agree** | `test_routing_contract.py` |
+| CP | Holdout/router expansion | **Reject** | — |
+| CQ | Playbook step 7 | **Agree** | `GLOSSARY.md` |
+| CR | Final seal | **Agree** | Panel resealed Round 67 |
+
+**All roles agree.**
+
+## Implemented Changes (Round 67)
+
+- `CONTRIBUTING.md`: Routing Maintenance R8–R12, cheatsheet parity step, fix duplicate numbering
+- `ROUTING_CONTRACT.md`: Related Artifacts — holdout YAMLs, zh-TW cheatsheet, parity tests
+- `plans/tests/test_routing_contract.py`: R8–R12 + related-artifacts anti-drift
+- `GLOSSARY.md`: playbook Rounds 1–67 + step 7
+- `test_glossary_structure.py`: Round 67 reference guard
+- `PROJECT_KNOWLEDGE.md`: Decision Index entry
+
+## Verification (Round 67)
+
+- `make all`: pytest + ROUTE-001/002/003 100%
+
 ## Panel status (updated)
 
-**Sealed 2026-06-25** after **Round 66** (options A–CL). Post-`cb6ea2b` quick-cue governance complete. Future work remains recurrence-gated maintenance per playbook.
+**Sealed 2026-06-25** after **Round 67** (options A–CR). Contributor/operator doc parity complete. Future work remains recurrence-gated maintenance per playbook.
 
 _Ongoing maintenance: [GLOSSARY.md](../GLOSSARY.md) Governance Maintenance Playbook — expand ROUTE-002/003 holdout before `route_paraphrase_eval.py` tuning (R8–R12)._
+

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

@@ -30,10 +30,10 @@ def test_round_boundary_terms_present(glossary_text: str):
         assert heading in glossary_text, f"missing glossary section: {heading}"
 
 
-def test_maintenance_playbook_references_round_66(glossary_text: str):
+def test_maintenance_playbook_references_round_67(glossary_text: str):
     playbook = glossary_text.split("## Governance Maintenance Playbook", 1)[1]
-    assert "Rounds 1–66" in playbook or "Rounds 1-66" in playbook
-    assert "Rounds 1–65" not in playbook and "Rounds 1-65" not in playbook
+    assert "Rounds 1–67" in playbook or "Rounds 1-67" in playbook
+    assert "Rounds 1–66" not in playbook and "Rounds 1-66" not in playbook
 
 
 def test_approved_spec_delivery_separated_from_playbook(glossary_text: str):

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

@@ -0,0 +1,43 @@
+"""Structural anti-drift tests for ROUTING_CONTRACT.md."""
+
+from pathlib import Path
+
+import pytest
+
+CONTRACT_PATH = Path(__file__).parent.parent / "ROUTING_CONTRACT.md"
+
+REQUIRED_RULES = (
+    "### R8: Holdout-before-tune",
+    "### R9: Production-negation and plan-only boundaries",
+    "### R10: Brief-before-plan",
+    "### R11: Approved-spec delivery",
+    "### R12: Boundary quick-cue summary",
+)
+
+
+@pytest.fixture(scope="module")
+def contract_text() -> str:
+    assert CONTRACT_PATH.is_file(), f"missing {CONTRACT_PATH}"
+    return CONTRACT_PATH.read_text(encoding="utf-8")
+
+
+def test_routing_boundary_rules_present(contract_text: str):
+    for heading in REQUIRED_RULES:
+        assert heading in contract_text, f"missing routing contract section: {heading}"
+
+
+def test_r12_mentions_cheatsheet_parity_tests(contract_text: str):
+    start = contract_text.index("### R12: Boundary quick-cue summary")
+    end = contract_text.index("## Router Output Contract", start)
+    section = contract_text[start:end]
+    assert "test_cheatsheet_boundary_quick_cues.py" in section
+    assert "test_cheatsheet_*_parity.py" in section
+
+
+def test_related_artifacts_include_cheatsheets_and_parity_tests(contract_text: str):
+    section = contract_text.split("## Related Artifacts", 1)[1]
+    assert "SKILL_TRIGGER_CHEATSHEET.zh-TW.md" in section
+    assert "test_cheatsheet_boundary_quick_cues.py" in section
+    assert "test_cheatsheet_*_parity.py" in section
+    assert "route-002-holdout-eval.yaml" in section
+    assert "route-003-adversarial-eval.yaml" in section