Round 79: bidirectional thinking-lens ↔ skill cross-links

johnteee · johnteee · commit 434cae5ae9b6 · 2026-06-25T15:58:23.000+08:00
- List consumer workflow skills in 01-thinking Purpose preambles
- Add THINKING_LENS_SKILL_CONSUMERS reciprocal pytest in test_prompt_cross_links
- Reseal panel, governance docs, GLOSSARY playbook step 10; pytest floor 440+
diff --git a/README.md b/README.md
@@ -21,7 +21,7 @@ Full library docs: [reflective-prompt-library/README.md](reflective-prompt-libra
 ## Governance
 
 - **Contributing:** [CONTRIBUTING.md](CONTRIBUTING.md) — quality gates, routing maintenance (R8–R12), `make all`
-- **Panel record:** [multi-agent-panel-consensus](reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md) — six-lens Socratic consensus (Rounds 1–78)
+- **Panel record:** [multi-agent-panel-consensus](reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md) — six-lens Socratic consensus (Rounds 1–79)
 - **Operator playbook:** [GLOSSARY.md](reflective-prompt-library/GLOSSARY.md) — Governance Maintenance Playbook
 
 The repository contains:
diff --git a/reflective-prompt-library/01-thinking/counterargument.md b/reflective-prompt-library/01-thinking/counterargument.md
@@ -4,7 +4,7 @@ Use this to prevent excessive optimism, overengineering, or AI flattery.
 
 ## Purpose
 
-Stress-test optimism, overengineering, and AI flattery before committing resources. Primary workflow surfaces: `reflective-review` and `reflective-minimality`; escalate to `reflective-risk` when trust-boundary or blast-radius signals appear.
+Stress-test optimism, overengineering, and AI flattery before committing resources. Primary workflow surfaces: `reflective-implement` for disputed implementation choices; `reflective-review` and `reflective-minimality` for critique and anti-bloat; escalate to `reflective-risk` when trust-boundary or blast-radius signals appear.
 
 ## Scope
 
diff --git a/reflective-prompt-library/01-thinking/critical-thinking-check.md b/reflective-prompt-library/01-thinking/critical-thinking-check.md
@@ -4,7 +4,7 @@ Use this to review articles, strategies, product ideas, technical choices, or AI
 
 ## Purpose
 
-Audit claims, assumptions, and evidence quality before accepting a plan, article, or AI output. Primary workflow surface: `reflective-review`; pair with `reflective-research` when external sources are required.
+Audit claims, assumptions, and evidence quality before accepting a plan, article, or AI output. Primary workflow surfaces: `reflective-review` for diff/plan critique; `reflective-implement` for evidence before material commits; `reflective-risk` for high-blast-radius checks; pair with `reflective-research` when external sources are required.
 
 ## Scope
 
diff --git a/reflective-prompt-library/01-thinking/socratic-reviewer.md b/reflective-prompt-library/01-thinking/socratic-reviewer.md
@@ -4,7 +4,7 @@ Suitable for requirements interviews, life decisions, product direction, busines
 
 ## Purpose
 
-Clarify the real question before choosing a direction. Primary workflow surfaces: `reflective-brief` for goal and assumption clarification; escalate to `reflective-spec-plan` when scope is clear enough to plan.
+Clarify the real question before choosing a direction. Primary workflow surfaces: `reflective-brief` for goal and assumption clarification; `reflective-dispatch` for routing; `reflective-research` for multi-voice synthesis; `reflective-handoff-retro` for session transfer; escalate to `reflective-spec-plan` when scope is clear enough to plan.
 
 ## Scope
 
diff --git a/reflective-prompt-library/01-thinking/why-what-how-done.md b/reflective-prompt-library/01-thinking/why-what-how-done.md
@@ -4,7 +4,7 @@ Use this as the core gate prompt before committing to a direction.
 
 ## Purpose
 
-Gate a task through Why / What / How / Done before choosing strictness or workflow depth. Primary workflow surfaces: `reflective-brief` then `reflective-dispatch` for orchestration level selection.
+Gate a task through Why / What / How / Done before choosing strictness or workflow depth. Primary workflow surfaces: `reflective-brief` then `reflective-dispatch` for orchestration level selection; `reflective-spec-plan` when framing becomes ticket or spec work.
 
 ## Scope
 
diff --git a/reflective-prompt-library/GLOSSARY.md b/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 1–68). Not agent instructions — operator checklist.
+Ongoing upkeep after panel close (Rounds 1–79). Not agent instructions — operator checklist.
 
 **Operational test:** Before router tuning, add fresh ROUTE-002/003 holdout phrases; run `make all`; record decisions in `PROJECT_KNOWLEDGE.md` Decision Index when governance surface changes.
 
@@ -350,4 +350,5 @@ Ongoing upkeep after panel close (Rounds 1–68). Not agent instructions — ope
 7. When holdout probe tuples change in `test_validate_route_fixture.py`, mirror cues in EN/zh-TW cheatsheets and run `test_cheatsheet_*_parity.py` (e.g. `test_cheatsheet_dispatch_meta_parity.py`).
 8. Keep `CONTRIBUTING.md` Routing Maintenance aligned with `ROUTING_CONTRACT.md` R8–R12 when boundaries or cheatsheet parity steps change.
 9. 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.
+10. When changing thinking-lens ↔ skill cross-links, update `SKILL_THINKING_SOURCES` and consumer lists in `01-thinking/` Purpose preambles; run `test_prompt_cross_links.py` (including reciprocal `THINKING_LENS_SKILL_CONSUMERS`).
 
diff --git a/reflective-prompt-library/PROJECT_KNOWLEDGE.md b/reflective-prompt-library/PROJECT_KNOWLEDGE.md
@@ -72,10 +72,12 @@ deferred promotions are recurrence-gated — see [panel backlog](plans/multi-age
 
 ## Decision Index
 
-- 2026-06-25 Round 78 panel — complete nine-skill thinking-lens cross-links + Module Contract anti-drift → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 > Pointers to the causal trail — plans, reflections, tests, commits. Detail is
 > not duplicated here; this is a map, not an archive.
 
+- 2026-06-25 Round 79 panel — bidirectional thinking-lens ↔ workflow skill preamble cross-links + reciprocal pytest → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
+- 2026-06-25 Round 78 panel — complete nine-skill thinking-lens cross-links + Module Contract anti-drift → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
+
 - 2026-06-25 Round 77 panel — governance pytest mirrors (`test_validate_governance.py`, `test_validate_links.py`, `test_lint_skills.py`) → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 76 panel — standardize `06-repo/` prompt contracts (Purpose/Scope/Acceptance/Falsifiability) + thinking/workflow cross-links + `test_repo_prompts_eval_harness.py` → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
 - 2026-06-25 Round 75 panel — standardize `05-domain/` prompt contracts (Purpose/Scope/Acceptance/Falsifiability) + thinking/workflow cross-links + `test_domain_prompts_eval_harness.py` → [record](plans/multi-agent-panel-consensus-2026-06-25.md)
diff --git a/reflective-prompt-library/README.md b/reflective-prompt-library/README.md
@@ -30,7 +30,7 @@ Pick **Strictness L1–L6** first (`skills/reflective-dispatch/SKILL.md`, [GLOSS
 
 ## Governance Panel Record
 
-Multi-agent Socratic consensus on project goals and the nine skills (Rounds 1–78, options A–ED) is recorded in [plans/multi-agent-panel-consensus-2026-06-25.md](plans/multi-agent-panel-consensus-2026-06-25.md). Run `make all` before claiming routing or governance changes are verified.
+Multi-agent Socratic consensus on project goals and the nine skills (Rounds 1–79, options A–EH) is recorded in [plans/multi-agent-panel-consensus-2026-06-25.md](plans/multi-agent-panel-consensus-2026-06-25.md). Run `make all` before claiming routing or governance changes are verified.
 
 ## Directory Map
 
diff --git a/reflective-prompt-library/plans/QUALITY_GATES_SUMMARY.md b/reflective-prompt-library/plans/QUALITY_GATES_SUMMARY.md
@@ -314,7 +314,7 @@ ROUTE-002 measures unseen phrasing separately from ROUTE-001. Round 7 (2026-06-2
 2. **ROUTE-001/002/003 in CI** — 128 + 102 + 53 paraphrases at 100% consistency (seeded fixtures); `validate_route_fixture.py` gates minimum coverage
 3. **Governance validators** — links, lint, governance metadata, PROJECT_KNOWLEDGE, benchmark fixture, skill examples
 4. **Harness policy docs** — CONTRIBUTING, AGENTS, SKILL_INSTALLATION, maintenance playbook
-5. **Doc anti-drift** — `test_routing_contract.py`, cheatsheet parity tests, `test_readme_governance.py`, `test_thinking_prompts_eval_harness.py`, `test_engineering_prompts_eval_harness.py`, `test_prompt_cross_links.py`, `test_core_prompts_eval_harness.py`, `test_agent_prompts_eval_harness.py`, `test_context_prompts_eval_harness.py`, `test_domain_prompts_eval_harness.py`, `test_repo_prompts_eval_harness.py`, `test_validate_governance.py`, `test_validate_links.py`, `test_lint_skills.py`, `test_skill_module_contract.py` (430+ pytest anti-drift suite in CI)
+5. **Doc anti-drift** — `test_routing_contract.py`, cheatsheet parity tests, `test_readme_governance.py`, `test_thinking_prompts_eval_harness.py`, `test_engineering_prompts_eval_harness.py`, `test_prompt_cross_links.py`, `test_core_prompts_eval_harness.py`, `test_agent_prompts_eval_harness.py`, `test_context_prompts_eval_harness.py`, `test_domain_prompts_eval_harness.py`, `test_repo_prompts_eval_harness.py`, `test_validate_governance.py`, `test_validate_links.py`, `test_lint_skills.py`, `test_skill_module_contract.py` (440+ pytest anti-drift suite in CI); reciprocal thinking-lens ↔ skill checks in `test_prompt_cross_links.py`
 
 ### Ongoing maintenance (not blockers)
 
@@ -384,4 +384,4 @@ Phase 1 quality-gate tooling and documentation are **complete**. Routing consist
 - ✅ Benchmark fixture gate plus optional manual benchmark runs
 - ✅ Research-backed design decisions
 
-The project is positioned to grow sustainably with quality discipline built in from the start. **No open implementation blockers** remain from panel Rounds 1–76; work is recurrence-gated maintenance per playbook. The next measurable quality target is **holdout expansion before router tuning** and optional manual baseline-vs-skill benchmark runs — not shipping new core skills without promotion evidence.
+The project is positioned to grow sustainably with quality discipline built in from the start. **No open implementation blockers** remain from panel Rounds 1–79; work is recurrence-gated maintenance per playbook. The next measurable quality target is **holdout expansion before router tuning** and optional manual baseline-vs-skill benchmark runs — not shipping new core skills without promotion evidence.
diff --git a/reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md b/reflective-prompt-library/plans/multi-agent-panel-consensus-2026-06-25.md
@@ -2063,3 +2063,48 @@ User directive (repeat): review prompts, plans, skills, and Socratic/critical-th
 
 **Resealed 2026-06-25** after **Round 78** (options EA–ED). Nine-skill thinking-lens cross-link pass complete; Module Contract anti-drift closed for core skills. Holdout expansion remains recurrence-gated maintenance.
 
+---
+
+## Round 79 — Bidirectional thinking-lens ↔ workflow skill cross-links (2026-06-25)
+
+**Options EE–EH** | Six-lens panel (Opus, Codex, Gemini, Composer, Sakana, GLM)
+
+### Round 79 options
+
+| ID | Proposal | Verdict |
+| --- | --- | --- |
+| EE | Bidirectional thinking-lens ↔ workflow-skill links (`01-thinking/` Purpose lists consumer skills; pytest inverts `SKILL_THINKING_SOURCES`) | **Agree** |
+| EF | Escalation subsection anti-drift (`lint_skills` suggestion only today) | **Defer** |
+| EG | ROUTE holdout expansion | **Defer** |
+| EH | Router / tenth skill / benchmark CI | **Reject** |
+
+### Round 79 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| EE | Bidirectional cross-links | **Agree** | Purpose preambles + reciprocal pytest |
+| EF | Escalation anti-drift | **Defer** | maintenance |
+| EG | Holdout expansion | **Defer** | maintenance |
+| EH | Router/tenth skill/benchmark CI | **Reject** | no change |
+
+**All roles agree.**
+
+## Implemented Changes (Round 79)
+
+- `01-thinking/socratic-reviewer.md`, `counterargument.md`, `critical-thinking-check.md`, `why-what-how-done.md`: Purpose preambles list primary consumer workflow skills
+- `plans/tests/test_prompt_cross_links.py`: `THINKING_LENS_SKILL_CONSUMERS` + `test_thinking_lens_preamble_lists_consumer_skills` reciprocal anti-drift
+- `GLOSSARY.md`: playbook Rounds 1–79; step 10 for reciprocal cross-links
+- `QUALITY_GATES_SUMMARY.md`: 440+ pytest floor; reciprocal cross-link note; panel Rounds 1–79
+- `PROJECT_KNOWLEDGE.md`: Decision Index Round 79 entry
+- `README.md`, `reflective-prompt-library/README.md`, `test_readme_governance.py`: panel round 79 sync
+
+## Verification (Round 79)
+
+- `make all`: pytest + ROUTE-001/002/003 100%
+
+## Panel status (updated)
+
+**Resealed 2026-06-25** after **Round 79** (options EE–EH). Bidirectional thinking-lens ↔ workflow skill cross-links complete; reciprocal pytest guards Purpose preambles. Holdout expansion and Escalation subsection anti-drift remain recurrence-gated maintenance.
+
+
+
diff --git a/reflective-prompt-library/plans/tests/test_glossary_structure.py b/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_68(glossary_text: str):
+def test_maintenance_playbook_references_round_79(glossary_text: str):
     playbook = glossary_text.split("## Governance Maintenance Playbook", 1)[1]
-    assert "Rounds 1–68" in playbook or "Rounds 1-68" in playbook
-    assert "Rounds 1–67" not in playbook and "Rounds 1-67" not in playbook
+    assert "Rounds 1–79" in playbook or "Rounds 1-79" in playbook
+    assert "Rounds 1–78" not in playbook and "Rounds 1-78" not in playbook
 
 
 
diff --git a/reflective-prompt-library/plans/tests/test_prompt_cross_links.py b/reflective-prompt-library/plans/tests/test_prompt_cross_links.py
@@ -278,6 +278,25 @@ def test_thinking_lens_files_exist_for_skill_links():
         assert (LIBRARY_ROOT / ref).is_file(), f"missing thinking lens file {ref}"
 
 
+def _invert_skill_thinking_sources() -> dict[str, tuple[str, ...]]:
+    consumers: dict[str, set[str]] = {}
+    for skill, lenses in SKILL_THINKING_SOURCES.items():
+        for lens in lenses:
+            consumers.setdefault(lens, set()).add(skill)
+    return {lens: tuple(sorted(skills)) for lens, skills in sorted(consumers.items())}
+
+
+THINKING_LENS_SKILL_CONSUMERS = _invert_skill_thinking_sources()
+
+
+@pytest.mark.parametrize("lens_ref,consumer_skills", THINKING_LENS_SKILL_CONSUMERS.items())
+def test_thinking_lens_preamble_lists_consumer_skills(lens_ref: str, consumer_skills: tuple[str, ...]):
+    """Reciprocal anti-drift: lenses name every workflow skill that cites them."""
+    preamble = _preamble(THINKING_DIR / Path(lens_ref).name)
+    for skill in consumer_skills:
+        assert skill in preamble, f"{lens_ref} preamble should reference consumer {skill}"
+
+
 @pytest.mark.parametrize("prompt_path", THINKING_PROMPTS, ids=lambda p: p.name)
 def test_thinking_prompt_maps_to_workflow_skill(prompt_path: Path):
     preamble = _preamble(prompt_path)
diff --git a/reflective-prompt-library/plans/tests/test_readme_governance.py b/reflective-prompt-library/plans/tests/test_readme_governance.py
@@ -10,8 +10,8 @@
 METHODOLOGY_MAP_EN = Path(__file__).parent.parent.parent / "METHODOLOGY_MAP.md"
 SKILL_MAP = Path(__file__).parent.parent.parent / "skills" / "skill-map.md"
 
-CURRENT_PANEL_ROUND = "78"
-CURRENT_PANEL_OPTIONS = "A–ED"
+CURRENT_PANEL_ROUND = "79"
+CURRENT_PANEL_OPTIONS = "A–EH"
 
 
 @pytest.fixture(scope="module")
