Round 78: nine-skill thinking cross-links + Module Contract anti-drift

Complete SKILL_THINKING_SOURCES coverage for all CORE_SKILLS, add
reflective-research Prompt Sources thinking lenses, and gate Module
Contract subsections with test_skill_module_contract.py.

Author: johnteee

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 1–77)
+- **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)
 - **Operator playbook:** [GLOSSARY.md](reflective-prompt-library/GLOSSARY.md) — Governance Maintenance Playbook
 
 The repository contains:

reflective-prompt-library/PROJECT_KNOWLEDGE.md

@@ -72,6 +72,7 @@ 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.
 

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 1–77, options A–DZ) 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 1–78, 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.
 
 ## Directory Map
 

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` (410+ 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` (430+ pytest anti-drift suite in CI)
 
 ### Ongoing maintenance (not blockers)
 

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

@@ -1994,3 +1994,72 @@ User directive (repeat): review prompts, plans, skills, and Socratic/critical-th
 ## Panel status (updated)
 
 **Resealed 2026-06-25** after **Round 77** (options DX–DZ). Governance validator pytest mirrors complete; prompt-library contract sweep and governance anti-drift suite closed. Holdout expansion before router tuning remains recurrence-gated maintenance.
+
+## Round 78 — Workflow skill thinking cross-links (2026-06-25)
+
+User directive (repeat): review prompts, plans, skills, and Socratic/critical-thinking lenses in parallel until all roles agree, then implement.
+
+### EA: Complete all nine workflow skill ↔ thinking-lens cross-links?
+
+| Lens | Position |
+| --- | --- |
+| Opus | **Agree** — Round 71 covered three skills; remaining six leave Socratic/critical lenses untested |
+| Codex | **Agree** — `SKILL_THINKING_SOURCES` parity with `CORE_SKILLS` is falsifiable |
+| Gemini | **Agree** — dispatch/brief/minimality lenses are cost-relevant entry points |
+| Composer | **Agree** — IDE users load skills with thinking lenses; reciprocal Prompt Sources required |
+| Sakana | **Agree** — research multi-voice method needs explicit socratic + critical-thinking links |
+| GLM | **Agree** — English canonical links; TW routing unaffected |
+
+**Socratic Q:** Why skills after prompt contract sweep?
+**Answer:** Skills are the harness-policy layer; thinking lenses must be traceable from every workflow skill Prompt Sources, not only implement/spec-plan/handoff.
+
+**Consensus:** **Agree** — extend `SKILL_THINKING_SOURCES` to all nine skills; add missing `reflective-research` Prompt Sources links; `test_all_workflow_skills_have_thinking_cross_link`.
+
+### EB: Skill Module Contract anti-drift for all nine skills?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Agree** — `lint_skills.py` warnings are not pytest-gated; bounded Trigger/Methods/Output/Never test |
+
+**Consensus:** **Agree** — `test_skill_module_contract.py` for all `CORE_SKILLS`.
+
+### EC: ROUTE-002/003 holdout expansion now?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Defer** — maintenance playbook item; this round targets skill ↔ thinking linkage |
+
+### ED: Router / holdout / tenth skill / benchmark CI?
+
+| Lens | Position |
+| --- | --- |
+| All six | **Reject** — unchanged |
+
+### Round 78 verdict table
+
+| ID | Option | Verdict | Action |
+| --- | --- | --- | --- |
+| EA | Nine-skill thinking cross-links | **Agree** | SKILL_THINKING_SOURCES + research Prompt Sources |
+| EB | Module Contract anti-drift | **Agree** | `test_skill_module_contract.py` |
+| EC | Holdout expansion | **Defer** | maintenance |
+| ED | Router/tenth skill/benchmark CI | **Reject** | no change |
+
+**All roles agree.**
+
+## Implemented Changes (Round 78)
+
+- `skills/reflective-research/SKILL.md`: add `01-thinking/socratic-reviewer.md` + `critical-thinking-check.md` to Prompt Sources
+- `plans/tests/test_prompt_cross_links.py`: `SKILL_THINKING_SOURCES` covers all nine `CORE_SKILLS`; lens file existence test
+- `plans/tests/test_skill_module_contract.py`: Module Contract + Trigger/Methods/Output/Never anti-drift
+- `QUALITY_GATES_SUMMARY.md`: skill cross-link + module contract tests; pytest floor 430+
+- `PROJECT_KNOWLEDGE.md`: Decision Index Round 78 entry
+- `README.md`, `reflective-prompt-library/README.md`, `test_readme_governance.py`: panel round 78 sync
+
+## Verification (Round 78)
+
+- `make all`: pytest + ROUTE-001/002/003 100%
+
+## Panel status (updated)
+
+**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.
+

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

@@ -28,15 +28,30 @@
 }
 
 SKILL_THINKING_SOURCES: dict[str, tuple[str, ...]] = {
+    "reflective-brief": (
+        "01-thinking/why-what-how-done.md",
+        "01-thinking/falsifiability.md",
+    ),
+    "reflective-dispatch": ("01-thinking/socratic-reviewer.md",),
+    "reflective-handoff-retro": ("01-thinking/socratic-reviewer.md",),
     "reflective-implement": (
         "01-thinking/counterargument.md",
         "01-thinking/critical-thinking-check.md",
     ),
+    "reflective-minimality": ("01-thinking/counterargument.md",),
+    "reflective-research": (
+        "01-thinking/socratic-reviewer.md",
+        "01-thinking/critical-thinking-check.md",
+    ),
+    "reflective-review": (
+        "01-thinking/critical-thinking-check.md",
+        "01-thinking/counterargument.md",
+    ),
+    "reflective-risk": ("01-thinking/critical-thinking-check.md",),
     "reflective-spec-plan": (
         "01-thinking/falsifiability.md",
         "01-thinking/why-what-how-done.md",
     ),
-    "reflective-handoff-retro": ("01-thinking/socratic-reviewer.md",),
 }
 
 
@@ -251,6 +266,18 @@ def test_workflow_skill_lists_thinking_sources(skill_name: str, thinking_refs: t
         assert ref in section, f"{skill_name} Prompt Sources should list {ref}"
 
 
+def test_all_workflow_skills_have_thinking_cross_link():
+    from validate_skill_examples import CORE_SKILLS  # noqa: WPS433
+
+    assert set(SKILL_THINKING_SOURCES) == set(CORE_SKILLS)
+
+
+def test_thinking_lens_files_exist_for_skill_links():
+    linked = {ref for refs in SKILL_THINKING_SOURCES.values() for ref in refs}
+    for ref in linked:
+        assert (LIBRARY_ROOT / ref).is_file(), f"missing thinking lens file {ref}"
+
+
 @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)

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 = "77"
-CURRENT_PANEL_OPTIONS = "A–DZ"
+CURRENT_PANEL_ROUND = "78"
+CURRENT_PANEL_OPTIONS = "A–ED"
 
 
 @pytest.fixture(scope="module")

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

@@ -0,0 +1,31 @@
+"""Anti-drift: all nine workflow skills keep Module Contract subsections."""
+
+import re
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from validate_skill_examples import CORE_SKILLS  # noqa: E402
+
+SKILLS_DIR = Path(__file__).parent.parent.parent / "skills"
+
+REQUIRED_SUBSECTIONS = ("Trigger", "Methods", "Output", "Never")
+
+
+@pytest.mark.parametrize("skill_name", CORE_SKILLS)
+def test_core_skill_has_module_contract(skill_name: str):
+    content = (SKILLS_DIR / skill_name / "SKILL.md").read_text(encoding="utf-8")
+    assert "## Module Contract" in content, skill_name
+
+
+@pytest.mark.parametrize("skill_name", CORE_SKILLS)
+def test_core_skill_has_contract_subsections(skill_name: str):
+    content = (SKILLS_DIR / skill_name / "SKILL.md").read_text(encoding="utf-8")
+    for subsection in REQUIRED_SUBSECTIONS:
+        pattern = rf"(##\s*{re.escape(subsection)}|^\*?\*?{re.escape(subsection)}:)"
+        assert re.search(pattern, content, re.MULTILINE | re.IGNORECASE), (
+            f"{skill_name} missing {subsection}"
+        )

reflective-prompt-library/skills/reflective-research/SKILL.md

@@ -163,3 +163,5 @@ Skip when the question is narrow, repo-local, and already has a single canonical
 - `03-context/gemini-long-document.md`
 - `04-agent/runtime-trust-boundary.md`
 - `04-agent/agent-scaffold-provenance.md`
+- `01-thinking/socratic-reviewer.md`
+- `01-thinking/critical-thinking-check.md`