feat(humanizer): update audit/analysis command templates group B [skip-docs]

Wave 5 Step 14. Threads the humanizer vocabulary through the remaining
six audit/analysis command templates and adds a shape test that locks
the structure plus a pair of anchor must-contains.

- commands/drift.md: --raw pass-through; new/resolved/changed-finding
  rendering instructions reference userActionLanguage and
  relevanceContext rather than raw severity.
- commands/plugin-health.md: --raw pass-through; finding rendering
  groups by userImpactCategory and leads with userActionLanguage.
- commands/config-audit.md (router): replaces the 25-line A/B/C/D/F
  prose ladder with a humanized stderr-scorecard reference + three
  userActionLanguage-grouped "What you can do next" branches; --raw
  threaded through both scan-orchestrator and posture invocations.
- commands/discover.md: --raw pass-through; finding-summary rendering
  groups by userImpactCategory.
- commands/analyze.md: --raw pass-through; analyzer-agent prompt now
  instructs grouping by userImpactCategory and leading with
  userActionLanguage; humanized title/description/recommendation
  strings rendered verbatim, no paraphrasing.
- commands/status.md: phase-label humanization table — current_phase
  machine field name preserved, user-facing labels translated
  ("Looking at your config files", "Working out what to recommend",
  "Asking what you'd like to focus on", "Putting together your action
  plan", "Making the changes", "Double-checking everything worked");
  --raw preserves verbatim machine field values.

tests/commands/group-b-shape.test.mjs (new, +8 tests, 772 → 780):
  - structural: bash block + Read tool + --raw/$ARGUMENTS plumbing
    across all 6 files
  - findings-renderers: humanized field reference + no grade-prose
  - anchor must-contains per plan: config-audit.md ⊇
    userImpactCategory|userActionLanguage; drift.md ⊇ --raw|humanized
  - status.md: current_phase preserved + ≥3 humanized phase labels

plugins/config-audit/commands/plugin-health.md

@@ -14,6 +14,7 @@ Audit Claude Code plugin structure and quality — validates plugin.json, CLAUDE
 
 - `$ARGUMENTS` may contain a path to a specific plugin directory
 - If omitted: scans all plugins in the marketplace root
+- `--raw`: pass-through to the scanner; produces v5.0.0 verbatim envelope (bypasses the humanizer) for byte-stable diff tooling
 
 ## Implementation
 
@@ -31,13 +32,15 @@ Auditing {N} plugin(s) for structure, frontmatter quality, and cross-plugin conf
 
 ### Step 2: Run scanner
 
-Run silently for each plugin:
+Run silently for each plugin. Default mode emits a humanized JSON envelope where each PLH finding carries `userImpactCategory`, `userActionLanguage`, and `relevanceContext` alongside the v5.0.0 fields. `--raw` is passed through verbatim when present.
 
 ```bash
-node ${CLAUDE_PLUGIN_ROOT}/scanners/plugin-health-scanner.mjs <path> 2>/dev/null
+RAW_FLAG=""
+if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
+node ${CLAUDE_PLUGIN_ROOT}/scanners/plugin-health-scanner.mjs <path> $RAW_FLAG 2>/dev/null
 ```
 
-Read stdout output (JSON). Parse findings.
+Read stdout output (JSON) using the Read tool. Parse findings.
 
 ### Step 3: Present results
 
@@ -59,10 +62,12 @@ Read stdout output (JSON). Parse findings.
 #### Findings by Plugin
 
 **{plugin-name}** ({finding_count} findings):
-1. [{id}] {title} — {recommendation}
+1. [{userActionLanguage}] {humanized title} ({id}) — {humanized recommendation}
 2. ...
 ```
 
+Group findings within each plugin by `userImpactCategory` (e.g., "Configuration mistake", "Conflict") and lead each line with `userActionLanguage` ("Fix this now", "Fix soon", "Optional cleanup"). The humanizer already produced the plain-language `title`/`recommendation` strings — render them verbatim, do not paraphrase.
+
 ### Step 4: Suggest next steps
 
 ```