docs(governance): Round 66 panel — R12 boundary quick-cue contract

Six-lens unanimous agreement after post-cb6ea2b rethink:
- ROUTING_CONTRACT R12: curated boundary quick-cue summary policy
- GLOSSARY Boundary Quick Cues + playbook step 6 (Rounds 1–66)
- Probe-snippet anti-drift in test_cheatsheet_boundary_quick_cues.py
- QUALITY_GATES 7.4 cheatsheet parity pytest mention
- Reject expanding quick-cue bullets (seven curated traps suffice)

167 pytest; ROUTE-001/002/003 remain 100%.

Author: johnteee

reflective-prompt-library/GLOSSARY.md

@@ -327,9 +327,17 @@ Routing boundary: when intent is to **implement or land an approved spec in the
 
 ---
 
+## Boundary Quick Cues / 邊界速查
+
+Curated top-of-cheatsheet summary of high-confusion routing traps (ROUTE-002 holdout + ROUTE-003 adversarial). Not exhaustive — per-skill trigger cues and holdout fixtures remain authoritative.
+
+**Operational test:** `test_cheatsheet_boundary_quick_cues.py` — marker labels and probe-linked snippets in the quick-cue block; `ROUTING_CONTRACT.md` R12.
+
+---
+
 ## Governance Maintenance Playbook / 治理維護手冊
 
-Ongoing upkeep after panel close (Rounds 1–65). Not agent instructions — operator checklist.
+Ongoing upkeep after panel close (Rounds 1–66). 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.
 
@@ -338,4 +346,5 @@ Ongoing upkeep after panel close (Rounds 1–65). Not agent instructions — ope
 3. Watch non-blocking undocumented-decision warnings from `validate_project_knowledge.py`.
 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`.
 

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 65 panel):** maintain ROUTE-001/002/003 evals, governance validators,
+**Ongoing (post Round 66 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 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)
 - 2026-06-25 Rounds 51–65 panel — brief-before-plan, design comparison, dispatch-meta, readme plain review holdouts → [record](plans/multi-agent-panel-consensus-2026-06-25.md)

reflective-prompt-library/plans/QUALITY_GATES_SUMMARY.md

@@ -227,6 +227,7 @@ python3 reflective-prompt-library/plans/route_paraphrase_eval.py reflective-prom
 - Current minimums: ROUTE-001 (12 intent + 4 adversarial groups, 128 phrases); ROUTE-002 (36 holdout groups, 100 phrases); ROUTE-003 (13 adversarial groups, 31 phrases)
 - Round 22 panel compromise: deterministic hygiene without YAML dependency explosion
 - Integrated in `make validate` after skill examples gate; mirrored by pytest in `test_validate_route_fixture.py`
+- Cheatsheet parity anti-drift: `test_cheatsheet_boundary_quick_cues.py` (R12 quick-cue summary), `test_cheatsheet_*_parity.py` (holdout probe cues in EN/zh-TW cheatsheets)
 
 **Usage:**
 ```bash

reflective-prompt-library/plans/ROUTING_CONTRACT.md

@@ -100,6 +100,18 @@ This contract applies to:
   still route to `reflective-spec-plan`.
 - Add ROUTE-003 `implement_not_plan_trap` holdout phrases (including mixed zh-TW + English approved-spec delivery) before tuning this boundary.
 
+### R12: Boundary quick-cue summary
+
+- `SKILL_TRIGGER_CHEATSHEET.md` and `.zh-TW.md` include a **curated** boundary quick-cue block
+  before the per-skill sections. It summarizes high-confusion ROUTE-002 holdout and ROUTE-003
+  adversarial traps; it is not an exhaustive list of all holdout phrases.
+- When adding a new routing boundary (R8–R11 pattern), update holdout fixtures and per-skill
+  trigger cues first; add a quick-cue bullet only when the trap is frequent enough to merit
+  top-of-page visibility.
+- Anti-drift: `plans/tests/test_cheatsheet_boundary_quick_cues.py` guards marker labels and
+  probe-linked snippets in the quick-cue block; `test_cheatsheet_*_parity.py` guards full
+  cheatsheet coverage.
+
 
 ## Router Output Contract
 

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

@@ -1162,8 +1162,108 @@ User directive: continue Socratic panel for as many rounds as feasible.
 
 - `make all`: **64 pytest**, ROUTE-001 **100%** (16/128), ROUTE-002 **100%** (36/100), ROUTE-003 **100%** (13/28)
 
-## Panel status (final)
+## Round 66 — Post quick-cue maintenance (2026-06-25)
 
-**Sealed 2026-06-25** after **Round 65** (options A–CF). Extended deliberation complete. Future work is recurrence-gated maintenance per playbook.
+User directive: **do anything you want** — reopen panel for post-`cb6ea2b` boundary quick-cue governance.
 
-_Ongoing maintenance: [GLOSSARY.md](../GLOSSARY.md) Governance Maintenance Playbook — expand ROUTE-002/003 holdout before `route_paraphrase_eval.py` tuning (R8–R11)._
+### CG: ROUTING_CONTRACT R12 — boundary quick-cue summary?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Agree** — curated quick-cue block is now a contract surface; document curated-not-exhaustive rule |
+| Codex | **Agree** — links holdout parity tests to routing contract |
+| Gemini | **Agree** — operators need explicit R12 before adding bullets ad hoc |
+| Composer | **Agree** — matches R8–R11 maintenance pattern |
+| Sakana | **Agree** — no new skill; contract only |
+| GLM | **Agree** — zh-TW cheatsheet included in R12 scope |
+
+**Socratic Q:** Does R12 duplicate cheatsheet content?
+**Answer:** No — it states *maintenance policy* (curated summary, holdout-first), not trigger cues.
+
+**Consensus:** **Agree** — add R12 to `ROUTING_CONTRACT.md`.
+
+### CH: Probe-linked anti-drift for quick-cue block?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Agree** — marker-only tests allow label drift from probe meaning |
+| Codex | **Agree** — `BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_*` tied to bullet descriptions |
+| Gemini | **Agree** — stronger than bold-label checks alone |
+| Composer | **Agree** — extend `test_cheatsheet_boundary_quick_cues.py` |
+| Sakana | **Agree** — exported from `test_validate_route_fixture.py` |
+| GLM | **Agree** — separate EN/zh-TW snippet tuples |
+
+**Consensus:** **Agree** — probe-snippet pytest guard.
+
+### CI: Expand quick cues (minimality, dispatch-meta, design comparison)?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Reject** — seven bullets suffice; skill sections + parity tests cover rest |
+| Codex | **Reject** — quick means quick; exhaustive list defeats purpose |
+| Gemini | **Defer** — would add three bullets |
+| Composer | **Reject** — R12 documents curated subset |
+| Sakana | **Reject** — holdout parity tests already guard full cues |
+| GLM | **Reject** — zh-TW summary already long enough |
+
+**Socratic Q:** If users miss minimality traps, do we expand quick cues?
+**Answer:** Per-skill sections and `test_cheatsheet_boundary_parity.py` already enforce those probes; expand holdout before router tune (R8), not quick-cue list.
+
+**Consensus:** **Reject expansion** — keep seven curated bullets.
+
+### CJ: GLOSSARY + maintenance playbook step?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Agree** — Boundary Quick Cues section + playbook step 6 |
+
+**Consensus:** **Agree**.
+
+### CK: QUALITY_GATES 7.4 mentions cheatsheet parity tests?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Agree** — document `test_cheatsheet_boundary_quick_cues.py` + `test_cheatsheet_*_parity.py` |
+
+**Consensus:** **Agree**.
+
+### CL: Re-litigate backlog (tenth skill, default minimality, benchmark CI, full i18n)?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Reject / Defer unchanged** — recurrence-gated backlog stands |
+
+**Consensus:** **Agree** — no backlog changes.
+
+### Round 66 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| CG | R12 boundary quick-cue contract | **Agree** | `ROUTING_CONTRACT.md` |
+| CH | Probe-snippet anti-drift | **Agree** | `test_validate_route_fixture.py` + `test_cheatsheet_boundary_quick_cues.py` |
+| CI | Expand quick-cue bullets | **Reject** | Keep curated seven |
+| CJ | GLOSSARY + playbook | **Agree** | Boundary Quick Cues + step 6 |
+| CK | QUALITY_GATES 7.4 sync | **Agree** | Cheatsheet parity pytest mention |
+| CL | Final seal | **Agree** | Panel resealed Round 66 |
+
+**All roles agree.**
+
+## Implemented Changes (Round 66)
+
+- `ROUTING_CONTRACT.md`: R12 Boundary quick-cue summary
+- `GLOSSARY.md`: Boundary Quick Cues section; playbook Rounds 1–66 + step 6
+- `test_validate_route_fixture.py`: `BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_EN/ZH`
+- `test_cheatsheet_boundary_quick_cues.py`: probe-snippet + count anti-drift tests
+- `test_glossary_structure.py`: Boundary Quick Cues section + Round 66 reference
+- `test_quality_gates_summary.py`: 7.4 cheatsheet parity mention guard
+- `QUALITY_GATES_SUMMARY.md`: 7.4 cheatsheet parity bullets
+
+## Verification (Round 66)
+
+- `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.
+
+_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_cheatsheet_boundary_quick_cues.py

@@ -9,6 +9,8 @@
 
 from test_validate_route_fixture import (  # noqa: E402
     BOUNDARY_QUICK_CUE_EN_MARKERS,
+    BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_EN,
+    BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_ZH,
     BOUNDARY_QUICK_CUE_ZH_MARKERS,
 )
 
@@ -44,3 +46,22 @@ def test_boundary_quick_cues_present_in_english_summary(en_boundary_quick_cues:
 @pytest.mark.parametrize("marker", BOUNDARY_QUICK_CUE_ZH_MARKERS)
 def test_boundary_quick_cues_present_in_zh_tw_summary(zh_boundary_quick_cues: str, marker: str):
     assert marker in zh_boundary_quick_cues, f"zh-TW boundary quick-cue summary missing: {marker!r}"
+
+@pytest.mark.parametrize("snippet", BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_EN)
+def test_boundary_quick_cue_probe_snippets_in_english_summary(en_boundary_quick_cues: str, snippet: str):
+    assert snippet.lower() in en_boundary_quick_cues.lower(), (
+        f"English boundary quick-cue summary missing probe snippet: {snippet!r}"
+    )
+
+
+@pytest.mark.parametrize("snippet", BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_ZH)
+def test_boundary_quick_cue_probe_snippets_in_zh_tw_summary(zh_boundary_quick_cues: str, snippet: str):
+    assert snippet.lower() in zh_boundary_quick_cues.lower(), (
+        f"zh-TW boundary quick-cue summary missing probe snippet: {snippet!r}"
+    )
+
+
+def test_boundary_quick_cue_probe_snippet_counts_match_markers():
+    assert len(BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_EN) == len(BOUNDARY_QUICK_CUE_EN_MARKERS) - 1
+    assert len(BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_ZH) == len(BOUNDARY_QUICK_CUE_ZH_MARKERS) - 1
+

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

@@ -23,16 +23,17 @@ def test_round_boundary_terms_present(glossary_text: str):
     required = (
         "## Brief-before-Plan",
         "## Approved-Spec Delivery",
+        "## Boundary Quick Cues",
         "## Governance Maintenance Playbook",
     )
     for heading in required:
         assert heading in glossary_text, f"missing glossary section: {heading}"
 
 
-def test_maintenance_playbook_references_round_65(glossary_text: str):
+def test_maintenance_playbook_references_round_66(glossary_text: str):
     playbook = glossary_text.split("## Governance Maintenance Playbook", 1)[1]
-    assert "Rounds 1–65" in playbook or "Rounds 1-65" in playbook
-    assert "Rounds 1–50" not in playbook and "Rounds 1-50" not in playbook
+    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
 
 
 def test_approved_spec_delivery_separated_from_playbook(glossary_text: str):

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

@@ -84,3 +84,13 @@ def test_ci_paraphrase_totals_match_route_minimums(summary_text: str):
         f"{ROUTE_001_MIN_PHRASES} + {ROUTE_002_MIN_PHRASES} + {ROUTE_003_MIN_PHRASES}"
     )
     assert expected_total in summary_text
+
+def test_route_fixture_gate_mentions_cheatsheet_parity_tests(summary_text: str):
+    section = _section_between(
+        summary_text,
+        "### 7.4 Route Fixture Gate ✅",
+        "### 7. Small Benchmark Set ✅",
+    )
+    assert "test_cheatsheet_boundary_quick_cues.py" in section
+    assert "test_cheatsheet_" in section and "_parity.py" in section
+

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

@@ -139,6 +139,27 @@ def test_round_51_boundary_probes():
     "**正式環境風險不是一般審查**",
 )
 
+# Probe-linked snippets that must appear in each quick-cue bullet description (R12 anti-drift).
+BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_EN = (
+    "explicit no-code context",
+    "production risk is out of scope",
+    "approved spec in the repository",
+    "before PRD/tickets",
+    "multi-voice debates",
+    "small code patches",
+    "auth/production/billing",
+)
+
+BOUNDARY_QUICK_CUE_PROBE_SNIPPETS_ZH = (
+    "明確不要改程式",
+    "排除正式環境風險",
+    "已核准 spec",
+    "PRD/工單前",
+    "多視角",
+    "小 patch",
+    "auth/production/billing",
+)
+
 
 def test_route_003_adversarial_boundary_probes():
     """Anti-drift: ROUTE-003 adversarial boundaries route as fixture expects."""