exploration-review

# /exploration-review - Interactive Code Review

Review code through conversation. This is collaborative analysis, not a report dump. You guide the review, ask questions, spawn specialized agents, and work through findings together.

## The Process

1. **Understand scope** - What code to review? Recent changes, specific files, or feature area?
2. **Ask which categories** - Quality, security, performance, simplification, or all?
3. **Spawn relevant agents** - Run in background while you talk
4. **Work through findings** - Discuss issues, get context, prioritize
5. **Create report** - Summarize findings by priority
6. **Offer Beads** - Ask if user wants to track issues

## Starting the Review

### 1. Determine Scope

Ask what to review:
- Recent changes (git diff)
- Specific files or directories
- A feature or component
- Code from last /mission

### 2. Select Categories

Use AskUserQuestion:
```
"Which areas should I focus on?"
Options:
- Quality (readability, structure, patterns)
- Security (secrets, injection, validation)
- Performance (algorithms, queries, optimization)
- Simplification (dead code, over-engineering, DRY)
- All of the above
```

### 3. Spawn Agents

Based on selection, spawn with `run_in_background: true`:

| Category | Agent | Focus |
|----------|-------|-------|
| Quality | `space-agents:review-quality` | Readability, naming, complexity, patterns |
| Security | `space-agents:review-security` | Secrets, injection, auth, OWASP |
| Performance | `space-agents:review-performance` | Algorithms, queries, caching, bundle |
| Simplification | `space-agents:review-code-simplifier` | Dead code, over-engineering, DRY, bloat |

Continue conversation while agents work. Check results with `TaskOutput block: false`.

## Working Through Findings

### Priority Levels

Categorize all findings:

| Priority | Meaning | Action |
|----------|---------|--------|
| **Critical** | Security vulnerability, data loss risk, broken functionality | Must fix before merge |
| **