gpt-5.3-codex review Phase 3

.github/skills/evidence-provenance-auditor/skill.md

@@ -24,8 +24,6 @@ Perform focused, deterministic audits of evidence integrity and provenance behav
 2. `docs/ver4/schema_v4.md`
 3. `docs/ver4/requirements_v4.md`
 4. `docs/ver4/error_handling_v4.md`
-5. `docs/ver4/history.md` (archive boundary)
-6. `docs-v4x-archive` tag (historical context only)
 
 ## Deterministic Pass/Fail Checks
 
@@ -61,19 +59,22 @@ Perform focused, deterministic audits of evidence integrity and provenance behav
 - Evidence-related model fields and semantics align with canonical docs.
 - Evidence model changes require same-change doc updates.
 
+### H. Canonical authority boundaries
+- Active guidance resolves against `docs/ver4/*` and current instruction files.
+
 ## Review Workflow
 
 1. Read normative references first.
 2. Inspect model + service + workflow write paths.
 3. Inspect evidence read/display/export paths.
 4. Report high-confidence findings with concrete path/line evidence.
-5. Classify each finding by invariant family (A-G).
+5. Classify each finding by invariant family (A-H).
 
 ## Output Format
 
 Use this structure:
 
-- Verdict by invariant family (A-G)
+- Verdict by invariant family (A-H)
 - Findings with `Location`, `Observed Behavior`, `Risk`, `Recommended Fix`
 - Drift table (`Doc claim` vs `Code reality` vs `Action`)
 - Regression guards needed

.github/skills/python-code-reviewer/skill.md

@@ -30,6 +30,7 @@ Perform thorough, evidence-based code reviews for Python projects. Every finding
 3. **Verify Claims:** Run or reference project tooling (`ruff check`, `ty`, `pytest`) rather than guessing.
 4. **Prioritize Hot Paths:** Focus deeply on request handling, database sessions, background workers, and external API calls.
 5. **Enforce Read-Only Safety:** Do not modify code unless explicitly instructed.
+6. **Escalate Provenance Audits:** For evidence/provenance-heavy changes, apply invariant checks from `.github/skills/evidence-provenance-auditor/skill.md` and include pass/fail outcomes in the report.
 
 ## Repo-Specific Deterministic Checks (Transcription)
 
@@ -39,10 +40,11 @@ When reviewing this repository, always include explicit pass/fail checks for:
 2. **UI boundary rule:** pages/components do not perform persistence access (`tests/test_ui_boundaries.py`).
 3. **Status vocabulary conformance:** `JobStatus`/`JobSourceStatus` usage matches current enums in `src/transcription/db/models.py`.
 4. **Evidence ownership conformance:** append-only attempt history is preserved and projection writes are not mistaken for history mutation (`src/transcription/services/sources.py`, `src/transcription/services/evidence.py`).
-5. **Canonical V4 authority:** findings must resolve against `docs/ver4/*` first, and treat `docs/ver4/history.md` plus `docs-v4x-archive` as historical context.
-6. **Media boundary conformance:** print/export media is record-validated and UI media URL generation uses controlled resolver paths.
-7. **Eager-loading conformance:** service/UI read paths satisfy `lazy="raise"` expectations.
-8. **Cross-cutting error conformance:** service/API/UI translation and retry behavior align with `.github/instructions/error-handling.instructions.md`.
+5. **Canonical V4 authority:** findings must resolve against `docs/ver4/*` first.
+6. **Schema contract fidelity:** when model/persistence behavior changes, `docs/ver4/schema_v4.md` remains field-accurate with `src/transcription/db/models.py`.
+7. **Media boundary conformance:** print/export media is record-validated and UI media URL generation uses controlled resolver paths.
+8. **Eager-loading conformance:** service/UI read paths satisfy `lazy="raise"` expectations.
+9. **Cross-cutting error conformance:** service/API/UI translation and retry behavior align with `.github/instructions/error-handling.instructions.md`.
 
 ## Core Review Areas