feat: cross-model outside voice in plan reviews (v0.9.9.1) (#326)

* feat: add generateCodexPlanReview() resolver for cross-model plan review

New resolver offers an optional Codex (or Claude subagent fallback) "outside
voice" after plan review sections complete. Includes cross-model tension
detection with auto-TODO proposals, review log persistence, and an Outside
Voice row in the Review Readiness Dashboard.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: integrate {{CODEX_PLAN_REVIEW}} into CEO and eng review templates

CEO review: insert after Section 11 + add Outside Voice summary row.
Eng review: replace hardcoded Step 0.5 with resolver (adds fallback,
logging, dashboard, xhigh reasoning, cross-model tension tracking).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: regenerate SKILL.md files from updated templates

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: update project documentation for v0.9.9.1

ARCHITECTURE.md: added {{CODEX_PLAN_REVIEW}} to placeholder table.
CHANGELOG.md: added v0.9.9.1 entry for outside voice feature.
VERSION: bumped to 0.9.9.1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: move {{CODEX_PLAN_REVIEW}} after review sections in eng review

Codex adversarial review caught that the placeholder was positioned
before the 4 review sections, so the "After all review sections are
complete" instruction could confuse the model. Moved it after Section
4's STOP directive where it belongs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: regenerate eng review SKILL.md files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

plan-eng-review/SKILL.md.tmpl

@@ -96,29 +96,6 @@ Before reviewing anything, answer these questions:
 
 If the complexity check triggers (8+ files or 2+ new classes/services), proactively recommend scope reduction via AskUserQuestion — explain what's overbuilt, propose a minimal version that achieves the core goal, and ask whether to reduce or proceed as-is. If the complexity check does not trigger, present your Step 0 findings and proceed directly to Section 1.
 
-### Step 0.5: Codex plan review (optional)
-
-Check if the Codex CLI is available: `which codex 2>/dev/null`
-
-If available, after presenting Step 0 findings, use AskUserQuestion:
-```
-Want an independent Codex (OpenAI) review of this plan before the detailed review?
-A) Yes — let Codex critique the plan independently
-B) No — proceed with the Claude review only
-```
-
-If the user chooses A: tell Codex to read the plan file itself (avoids ARG_MAX limits for large plans):
-```bash
-codex exec "You are a brutally honest technical reviewer. Read the plan file at <plan-file-path> and review it for: logical gaps and unstated assumptions, missing error handling or edge cases, overcomplexity (is there a simpler approach?), feasibility risks (what could go wrong?), and missing dependencies or sequencing issues. Be direct. Be terse. No compliments. Just the problems." -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached
-```
-
-Replace `<plan-file-path>` with the actual path to the plan file detected earlier. Codex has filesystem access in read-only mode and will read the file itself.
-
-Present the full output under a `CODEX SAYS (plan review):` header. Note any concerns
-that should inform the subsequent engineering review sections.
-
-If Codex is not available, skip silently.
-
 Always work through the full interactive review: one section at a time (Architecture → Code Quality → Tests → Performance) with at most 8 top issues per section.
 
 **Critical: Once the user accepts or rejects a scope reduction recommendation, commit fully.** Do not re-argue for smaller scope during later review sections. Do not silently reduce scope or skip planned components.
@@ -165,6 +142,8 @@ Evaluate:
 
 **STOP.** For each issue found in this section, call AskUserQuestion individually. One issue per call. Present options, state your recommendation, explain WHY. Do NOT batch multiple issues into one AskUserQuestion. Only proceed to the next section after ALL issues in this section are resolved.
 
+{{CODEX_PLAN_REVIEW}}
+
 ## CRITICAL RULE — How to ask questions
 Follow the AskUserQuestion format from the Preamble above. Additional rules for plan reviews:
 * **One issue = one AskUserQuestion call.** Never combine multiple issues into one question.
@@ -220,6 +199,7 @@ At the end of the review, fill in and display this summary so the user can see a
 - What already exists: written
 - TODOS.md updates: ___ items proposed to user
 - Failure modes: ___ critical gaps flagged
+- Outside voice: ran (codex/claude) / skipped
 - Lake Score: X/Y recommendations chose complete option
 
 ## Retrospective learning