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/plan.md

@@ -1,7 +1,7 @@
 ---
 name: config-audit:plan
 description: Phase 4 - Generate prioritized action plan with risk assessment
-allowed-tools: Read, Write, Glob, Grep, Agent
+allowed-tools: Read, Write, Glob, Grep, Agent, Bash
 model: opus
 ---
 
@@ -14,11 +14,15 @@ Generate a prioritized action plan based on analysis results.
 - Must have completed Phase 2 (analysis)
 - Phase 3 (interview) is optional — plan works with or without it
 
+## Arguments
+
+- `$ARGUMENTS` may contain `--raw` to forward to the planner-agent's instructions; in `--raw` mode the agent renders v5.0.0 verbatim severity prefiks instead of humanized `userActionLanguage` urgency phrasing.
+
 ## Implementation
 
 ### Step 1: Verify session state
 
-Find the most recent session with analysis completed. If none found: "No analysis results found. Run `/config-audit` first to scan your configuration."
+Find the most recent session with analysis completed using the Read tool on `~/.claude/config-audit/sessions/*/state.yaml`. If none found: "No analysis results found. Run `/config-audit` first to scan your configuration."
 
 ### Step 2: Tell the user what's happening
 
@@ -29,7 +33,12 @@ Building a prioritized plan based on your analysis results...
 Actions are ordered by impact, with risk assessment and dependency tracking.
 ```
 
-### Step 3: Spawn planner agent
+### Step 3: Parse flags and spawn planner agent
+
+```bash
+RAW_FLAG=""
+if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
+```
 
 Tell the user: **"Generating your action plan (this takes about 30 seconds)..."**
 
@@ -40,8 +49,18 @@ Agent(subagent_type: "config-audit:planner-agent")
     Generate action plan based on:
     - Analysis: ~/.claude/config-audit/sessions/{session-id}/analysis-report.md
     - Interview: ~/.claude/config-audit/sessions/{session-id}/interview.md (if exists)
-    Create prioritized plan with:
-    - Risk assessment per action (low/medium/high)
+    Mode: $RAW_FLAG (empty = humanized; "--raw" = v5.0.0 verbatim severity prefiks)
+    Create a prioritized plan that consumes the humanized finding fields:
+    - Group actions by userImpactCategory (e.g., "Configuration mistake",
+      "Conflict", "Wasted tokens", "Missed opportunity", "Dead config")
+    - Lead each action with userActionLanguage ("Fix this now," "Fix soon,"
+      "Fix when convenient," "Optional cleanup," "FYI") rather than raw
+      severity. The humanizer already replaced jargon-heavy
+      title/description/recommendation strings with plain-language
+      equivalents — render them verbatim, do not paraphrase.
+    - Surface relevanceContext when it isn't "affects-everyone" so the
+      user knows whether a fix touches shared config or just their machine
+    - Include risk assessment per action (low/medium/high)
     - Rollback strategy
     - Dependency ordering
     - Effort estimates