---
name: config-audit:analyze
description: Phase 2 - Generate analysis report with hierarchy map and issue detection
allowed-tools: Read, Write, Edit, Glob, Grep, Agent
model: opus
---

# Config-Audit: Analysis (Phase 2)

Generate comprehensive analysis report from discovery findings.

## Prerequisites

- Must have completed Phase 1 (discovery)
- Findings must exist in `~/.claude/config-audit/sessions/{session-id}/findings/`

## Arguments

- `$ARGUMENTS` may contain `--raw` to forward to the analyzer 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

Read `~/.claude/config-audit/sessions/{session-id}/state.yaml` using the Read tool and verify discovery phase completed. If not, tell the user: "Discovery hasn't been run yet. Start with `/config-audit discover` or just run `/config-audit` for a full audit."

### Step 2: Tell the user what's happening

```
## Analyzing Configuration

Reading your scan findings and generating a detailed analysis report...
This includes hierarchy mapping, conflict detection, and prioritized recommendations.
```

### Step 3: Spawn analyzer agent

Tell the user: **"Generating analysis (this takes about 30 seconds)..."**

```bash
RAW_FLAG=""
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
```

```
Agent(subagent_type: "config-audit:analyzer-agent")
  model: sonnet
  prompt: |
    Analyze all findings in: ~/.claude/config-audit/sessions/{session-id}/findings/
    Mode: $RAW_FLAG (empty = humanized; "--raw" = v5.0.0 verbatim severity prefiks)
    Generate comprehensive report covering:
    1. Executive summary with key metrics, grouped by userImpactCategory
    2. Hierarchy map visualization
    3. Conflict detection across config layers
    4. CLAUDE.md quality assessment
    5. Security issues (secrets, permissions)
    6. Top 10 prioritized recommendations — lead each item with the
       finding's 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.
    Return the complete report as your final message. Do not write it
    to a file — the orchestrating command saves it to the session directory.
```

### Step 4: Save the report

The agent returns the complete report as its final message — the Claude Code
subagent harness instructs agents not to write report/analysis files themselves,
so the command must persist it. Write the returned report verbatim (no edits,
no truncation) to `~/.claude/config-audit/sessions/{session-id}/analysis-report.md`
using the Write tool. Downstream phases (`plan`, `interview`, `status`) read this file.

### Step 5: Present summary

After saving the report, show a brief summary:

```markdown
### Analysis Complete

Report generated with:
- {N} conflicts detected
- {N} optimization opportunities
- {N} security notes
- Top recommendation: {first recommendation}

Full report: `~/.claude/config-audit/sessions/{session-id}/analysis-report.md`

### What's next

- **`/config-audit plan`** — Turn findings into a prioritized action plan
- **`/config-audit fix`** — Auto-fix deterministic issues right away
```

### Step 6: Update state

Update `state.yaml` with `current_phase: "analyze"`, `next_phase: "plan"`.