feat(humanizer): update action command templates [skip-docs]

Wave 5 Step 15. Threads --raw plumbing through all seven action
command templates and adds a shape test covering structural plumbing
plus help.md's plain-language vocabulary.

- commands/fix.md: --raw flag parsed; fix-plan rendering groups by
  userActionLanguage; humanized title/description/recommendation are
  rendered verbatim from the cross-referenced scan envelope.
- commands/rollback.md: terminology pass — "manifest" → "list of
  changes" in user-facing copy; the file name manifest.yaml is kept
  as the machine contract; --raw threaded through.
- commands/plan.md: --raw forwarded to the planner-agent's prompt;
  agent now instructed to group actions by userImpactCategory and
  lead with userActionLanguage; bash block added for flag parsing.
- commands/implement.md: --raw forwarded to the implementer-agent's
  prompt; progress-log lines now reference the humanized titles
  already present in the action plan.
- commands/cleanup.md: --raw accepted as no-op (cleanup is
  file-management only, no findings prose); bash block added.
- commands/help.md: full plain-language pass — "PreToolUse" and
  "frontmatter" jargon removed from user-facing copy; new
  vocabulary table surfaces the humanized userImpactCategory and
  userActionLanguage labels ("Configuration mistake", "Conflict",
  "Wasted tokens", "Missed opportunity", "Dead config" / "Fix this
  now", "Fix soon", "Fix when convenient", "Optional cleanup",
  "FYI"); --raw documented as global pass-through flag.
- commands/interview.md: --raw accepted as no-op; "unused hooks"
  question phrased as "unused automation that runs at specific
  events" in user-facing copy.

tests/commands/action-commands-shape.test.mjs (new, +6 tests, 780 → 786):
  - structural: bash block + Read tool + --raw/$ARGUMENTS plumbing
    across all 7 files
  - help.md vocabulary: ≥3 userImpactCategory labels and ≥3
    userActionLanguage phrases present
  - help.md jargon: no bare "PreToolUse" or "frontmatter" in copy

plugins/config-audit/commands/interview.md

@@ -1,7 +1,7 @@
 ---
 name: config-audit:interview
 description: Phase 3 - Interactive interview to gather user preferences
-allowed-tools: Read, Write, Edit, AskUserQuestion
+allowed-tools: Read, Write, Edit, AskUserQuestion, Bash
 model: sonnet
 ---
 
@@ -17,10 +17,21 @@ AskUserQuestion requires synchronous terminal interaction and does not work when
 ## Prerequisites
 
 - Must have completed Phase 2 (analysis)
-- Read analysis from `~/.claude/config-audit/sessions/{session-id}/analysis-report.md`
+- Use the Read tool on the analysis at `~/.claude/config-audit/sessions/{session-id}/analysis-report.md`
+
+## Arguments
+
+- `$ARGUMENTS` may contain `--raw` — pass-through accepted for CLI surface consistency. Interview is interactive prose only (no scanner output, no findings prose), so `--raw` is a no-op here.
 
 ## Implementation Steps
 
+0. **Parse flags**:
+
+   ```bash
+   RAW_FLAG=""
+   if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
+   ```
+
 1. **Load session state**: Verify analysis phase completed, read analysis report for context
 2. **Conduct interview inline**: Use AskUserQuestion tool directly (NOT via Task). Adapt questions based on analysis findings.
 3. **Save interview results**: Write to `~/.claude/config-audit/sessions/{session-id}/interview.md`
@@ -29,10 +40,10 @@ AskUserQuestion requires synchronous terminal interaction and does not work when
 
 ## Interview Questions
 
-Ask these using AskUserQuestion (skip questions that don't apply based on analysis):
+Ask these using AskUserQuestion (skip questions that don't apply based on analysis). Where the analysis report references finding IDs, use the humanized title from the report rather than re-deriving prose:
 
 1. **Config Style** — Centralized vs Distributed vs Hybrid organization
-2. **Unused Hooks** — Wire up, review individually, delete, or leave (only if found)
+2. **Unused automation that runs at specific events** — Wire up, review individually, delete, or leave (only if the analysis report flagged one)
 3. **Duplicate Permissions** — Remove from local, consolidate, or keep (only if found)
 4. **Modular Rules** — Use .claude/rules/ pattern? Yes/No
 5. **Path-Scoped Rules** — Which patterns (tests, src, config, docs) — only if Q4=Yes