feat: /design-consultation — risk-taking thesis, visual research, ambitious preview

Add SAFE/RISK breakdown to design proposals so users see which choices
match category conventions vs. which are deliberate creative departures.

Wire browse binary for visual competitive research — agent browses
competitor sites, takes screenshots, and analyzes fonts/colors/spacing
with graceful degradation to WebSearch-only or built-in knowledge.

Upgrade preview page instructions to render realistic product mockups
(dashboards, marketing pages, settings forms) instead of just swatches.

Rewrite README section with the thesis: "coherence is table stakes —
the real question is where you take risks."

plan-eng-review/SKILL.md.tmpl

@@ -89,8 +89,7 @@ For LLM/prompt changes: check the "Prompt/LLM changes" file patterns listed in C
 After producing the test diagram, write a test plan artifact to the project directory so `/qa` and `/qa-only` can consume it as primary test input (replacing the lossy git-diff heuristic):
 
 ```bash
-SLUG=$(git remote get-url origin 2>/dev/null | sed 's|.*[:/]\([^/]*/[^/]*\)\.git$|\1|;s|.*[:/]\([^/]*/[^/]*\)$|\1|' | tr '/' '-')
-BRANCH=$(git rev-parse --abbrev-ref HEAD)
+eval $(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)
 USER=$(whoami)
 DATETIME=$(date +%Y%m%d-%H%M%S)
 mkdir -p ~/.gstack/projects/$SLUG
@@ -194,5 +193,24 @@ Check the git log for this branch. If there are prior commits suggesting a previ
 * One sentence max per option. Pick in under 5 seconds.
 * After each review section, pause and ask for feedback before moving on.
 
+## Review Log
+
+After producing the Completion Summary above, persist the review result:
+
+```bash
+eval $(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)
+mkdir -p ~/.gstack/projects/$SLUG
+echo '{"skill":"plan-eng-review","timestamp":"TIMESTAMP","status":"STATUS","unresolved":N,"critical_gaps":N,"mode":"MODE"}' >> ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
+```
+
+Substitute values from the Completion Summary:
+- **TIMESTAMP**: current ISO 8601 datetime
+- **STATUS**: "clean" if 0 unresolved decisions AND 0 critical gaps; otherwise "issues_open"
+- **unresolved**: number from "Unresolved decisions" count
+- **critical_gaps**: number from "Failure modes: ___ critical gaps flagged"
+- **MODE**: SCOPE_REDUCTION / BIG_CHANGE / SMALL_CHANGE
+
+{{REVIEW_DASHBOARD}}
+
 ## Unresolved decisions
 If the user does not respond to an AskUserQuestion or interrupts to move on, note which decisions were left unresolved. At the end of the review, list these as "Unresolved decisions that may bite you later" — never silently default to an option.