feat: community PRs — faster install, skill namespacing, uninstall, Codex fallback, Windows fix, Python patterns (v0.12.9.0) (#561)

* fix: sync package.json version with VERSION file (0.12.7.0)

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

* perf: shallow clone for faster install (#484)

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

* feat: Python/async/SSRF patterns in review checklist (#531)

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

* feat: namespace skill symlinks with gstack- prefix (#503)

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

* feat: add uninstall script (#323)

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

* feat: office-hours Claude subagent fallback when Codex unavailable (#464)

Updates generateCodexSecondOpinion resolver to always offer second opinion
and fall back to Claude subagent when Codex is unavailable or errors.

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

* fix: findPort() race condition via net.createServer (#490)

Replaces Bun.serve() port probing with net.createServer() for proper
async bind/close semantics. Fixes Windows EADDRINUSE race condition.

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

* test: add tests for uninstall, setup prefix, and resolver fallback

- Uninstall integration tests: syntax, flags, mock install layout, upgrade path
- Setup prefix tests: gstack-* prefixing, --no-prefix, cleanup migration
- Resolver tests: Claude subagent fallback in generated SKILL.md

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

* chore: bump version and changelog (v0.12.9.0)

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

---------

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

scripts/resolvers/review.ts

@@ -251,21 +251,19 @@ export function generateCodexSecondOpinion(ctx: TemplateContext): string {
 
   return `## Phase 3.5: Cross-Model Second Opinion (optional)
 
-**Binary check first — no question if unavailable:**
+**Binary check first:**
 
 \`\`\`bash
 which codex 2>/dev/null && echo "CODEX_AVAILABLE" || echo "CODEX_NOT_AVAILABLE"
 \`\`\`
 
-If \`CODEX_NOT_AVAILABLE\`: skip Phase 3.5 entirely — no message, no AskUserQuestion. Proceed directly to Phase 4.
+Use AskUserQuestion (regardless of codex availability):
 
-If \`CODEX_AVAILABLE\`: use AskUserQuestion:
-
-> Want a second opinion from a different AI model? Codex will independently review your problem statement, key answers, premises, and any landscape findings from this session. It hasn't seen this conversation — it gets a structured summary. Usually takes 2-5 minutes.
+> Want a second opinion from an independent AI perspective? It will review your problem statement, key answers, premises, and any landscape findings from this session without having seen this conversation — it gets a structured summary. Usually takes 2-5 minutes.
 > A) Yes, get a second opinion
 > B) No, proceed to alternatives
 
-If B: skip Phase 3.5 entirely. Remember that Codex did NOT run (affects design doc, founder signals, and Phase 4 below).
+If B: skip Phase 3.5 entirely. Remember that the second opinion did NOT run (affects design doc, founder signals, and Phase 4 below).
 
 **If A: Run the Codex cold read.**
 
@@ -303,15 +301,26 @@ cat "$TMPERR_OH"
 rm -f "$TMPERR_OH" "$CODEX_PROMPT_FILE"
 \`\`\`
 
-**Error handling:** All errors are non-blocking — Codex second opinion is a quality enhancement, not a prerequisite.
-- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key": "Codex authentication failed. Run \\\`codex login\\\` to authenticate. Skipping second opinion."
-- **Timeout:** "Codex timed out after 5 minutes. Skipping second opinion."
-- **Empty response:** "Codex returned no response. Stderr: <paste relevant error>. Skipping second opinion."
+**Error handling:** All errors are non-blocking — second opinion is a quality enhancement, not a prerequisite.
+- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key": "Codex authentication failed. Run \\\`codex login\\\` to authenticate." Fall back to Claude subagent.
+- **Timeout:** "Codex timed out after 5 minutes." Fall back to Claude subagent.
+- **Empty response:** "Codex returned no response." Fall back to Claude subagent.
 
-On any error, proceed to Phase 4 — do NOT fall back to a Claude subagent (this is brainstorming, not adversarial review).
+On any Codex error, fall back to the Claude subagent below.
+
+**If CODEX_NOT_AVAILABLE (or Codex errored):**
+
+Dispatch via the Agent tool. The subagent has fresh context — genuine independence.
+
+Subagent prompt: same mode-appropriate prompt as above (Startup or Builder variant).
+
+Present findings under a \`SECOND OPINION (Claude subagent):\` header.
+
+If the subagent fails or times out: "Second opinion unavailable. Continuing to Phase 4."
 
 4. **Presentation:**
 
+If Codex ran:
 \`\`\`
 SECOND OPINION (Codex):
 ════════════════════════════════════════════════════════════
@@ -319,10 +328,18 @@ SECOND OPINION (Codex):
 ════════════════════════════════════════════════════════════
 \`\`\`
 
-5. **Cross-model synthesis:** After presenting Codex output, provide 3-5 bullet synthesis:
-   - Where Claude agrees with Codex
+If Claude subagent ran:
+\`\`\`
+SECOND OPINION (Claude subagent):
+════════════════════════════════════════════════════════════
+<full subagent output, verbatim — do not truncate or summarize>
+════════════════════════════════════════════════════════════
+\`\`\`
+
+5. **Cross-model synthesis:** After presenting the second opinion output, provide 3-5 bullet synthesis:
+   - Where Claude agrees with the second opinion
    - Where Claude disagrees and why
-   - Whether Codex's challenged premise changes Claude's recommendation
+   - Whether the challenged premise changes Claude's recommendation
 
 6. **Premise revision check:** If Codex challenged an agreed premise, use AskUserQuestion: