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/drift.md

@@ -16,6 +16,7 @@ Compare current configuration against a saved baseline to see what changed.
   - A target path (default: current working directory)
   - `--save`: Save current state as baseline
   - `--baseline <name>`: Compare against a specific named baseline (default: "default")
+  - `--raw`: Pass-through to the scanner; produces v5.0.0 verbatim diff output (bypasses the humanizer). Use when piping into v5.0.0-baseline diff tooling that depends on byte-stable output.
 
 ## Implementation
 
@@ -26,7 +27,9 @@ If `--save` is present:
 Tell the user: **"Saving current configuration as baseline..."**
 
 ```bash
-node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --save --name <baseline-name> 2>/dev/null
+RAW_FLAG=""
+if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
+node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --save --name <baseline-name> $RAW_FLAG 2>/dev/null
 ```
 
 Read stdout for confirmation. Tell the user:
@@ -45,17 +48,21 @@ Without `--save`:
 Tell the user: **"Comparing current configuration against baseline..."**
 
 ```bash
-node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --baseline <name> 2>/dev/null
+RAW_FLAG=""
+if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
+node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --baseline <name> $RAW_FLAG 2>/dev/null
 ```
 
-Read stdout. If baseline not found, tell the user:
+Read stdout. In default mode the diff sections are humanized — finding titles, descriptions, and recommendations have already been replaced with plain-language equivalents. New/resolved/changed finding lists carry `userImpactCategory`, `userActionLanguage`, and `relevanceContext` so you can group and prioritize without re-deriving severity prose. If `--raw` was passed, the v5.0.0 diff is verbatim — present it in a code block as-is.
+
+If baseline not found, tell the user:
 
 ```
 No baseline found. Save one first with:
   /config-audit drift --save
 ```
 
-Otherwise, parse and present the drift report:
+Otherwise, parse and present the drift report. Use the Read tool on the captured stdout (or pipe it into a tmpfile first if you prefer):
 
 ```markdown
 ### Configuration Drift
@@ -65,15 +72,15 @@ Otherwise, parse and present the drift report:
 
 {If new findings:}
 #### New Issues ({count})
-| ID | Severity | Description |
-|----|----------|-------------|
-| ... | ... | ... |
+| ID | Action | Description |
+|----|--------|-------------|
+| {id} | {userActionLanguage — "Fix this now", "Fix soon", etc.} | {humanized title} |
 
 {If resolved findings:}
 #### Resolved ({count})
 | ID | Description |
 |----|-------------|
-| ... | ... |
+| {id} | {humanized title} |
 
 {If area changes:}
 #### Area Changes
@@ -82,6 +89,8 @@ Otherwise, parse and present the drift report:
 | ... | ... | ... | ... |
 ```
 
+When iterating new/resolved findings, prefer `userActionLanguage` over raw `severity` for the "Action" column — the humanizer already mapped severity to plain-language phrasing, and surfacing it consistently keeps the toolchain coherent. Mention `relevanceContext` when it isn't `affects-everyone` (the user wants to know if a fix touches shared config or just their machine).
+
 ### List baselines
 
 If `$ARGUMENTS` contains `--list`: