plan

# Plan - Intelligent Plan Builder

**Creates strategic execution plans based on user intent. Saves plans for review and optional execution with /octo:embrace.**

## Key Behavior

- **Creates plans** - Captures intent, analyzes requirements, generates weighted execution strategy
- **Saves to files** - Stores plan (`.claude/session-plan.md`) and intent contract (`.claude/session-intent.md`)
- **Doesn't execute** - Plans are saved for review; execution requires user confirmation
- **Optional execution** - Can invoke `/octo:embrace` immediately or user can execute later

## 🤖 INSTRUCTIONS FOR CLAUDE

### MANDATORY COMPLIANCE — DO NOT SKIP

**When the user explicitly invokes `/octo:plan`, you MUST execute the structured planning workflow below.** You are PROHIBITED from doing the task directly, skipping the intent capture questions, or deciding the task is "too simple" for structured planning. The user chose this command deliberately — respect that choice.

---

When the user invokes this command (e.g., `/octo:plan <arguments>`):

### Step 1: Capture Comprehensive Intent

**CRITICAL: Start by capturing the user's full intent using structured questions.**

Ask 5 comprehensive questions to understand what they're trying to accomplish:

```javascript
AskUserQuestion({
  questions: [
    {
      question: "What are you ultimately trying to accomplish?",
      header: "Goal",
      multiSelect: false,
      options: [
        {label: "Research a topic", description: "Gather information and options"},
        {label: "Make a decision", description: "Choose between alternatives"},
        {label: "Build something", description: "Create implementation or artifact"},
        {label: "Review/improve existing", description: "Assess and enhance what's there"},
        {label: "I'll describe it", description: "Let me write my own goal"}
      ]
    },
    {
      question: "How much do you already know about this?",
      header: "Knowledge",
      multiSelect: false,
      options: [
        {label: "Just starting", description: "Need to learn the landscape"},
        {label: "Some familiarity", description: "Know basics, need deeper dive"},
        {label: "Well-informed", description: "Know options, need execution"},
        {label: "Expert", description: "Just need implementation/validation"}
      ]
    },
    {
      question: "How clear is the scope?",
      header: "Clarity",
      multiSelect: false,
      options: [
        {label: "Vague idea", description: "Not sure exactly what I need"},
        {label: "General direction", description: "Know the area, need specifics"},
        {label: "Clear requirements", description: "Know what to build"},
        {label: "Fully specified", description: "Have detailed specifications"}
      ]
    },
    {
      question: "What defines success for you?",
      header: "Success",
      multiSelect: true,
      options: [
        {label: "Clear understanding", description: "I know what to do next"},
        {label: "Team alignment", description: "Everyone agrees on approach"},
        {label: "Working solution", description: "Implementation that functions"},
        {label: "Production-ready", description: "Fully tested and validated"}
      ]
    },
    {
      question: "What are your key constraints?",
      header: "Constraints",
      multiSelect: true,
      options: [
        {label: "Time pressure", description: "Need results quickly"},
        {label: "Must fit architecture", description: "Constrained by existing systems"},
        {label: "Team skill set", description: "Limited by team capabilities"},
        {label: "High stakes", description: "Significant risk if wrong"}
      ]
    }
  ]
})
```

**If user selected "I'll describe it" for goal, follow up with:**
```
Can you describe in 1-2 sentences what you're trying to accomplish?
```

### Step 2: Create Intent Contract

**Use the skill-intent-contract system to capture this formally:**

1. Create `.claude/session-intent.md` with:
   - Job statement (what user is trying to accomplish)
   - Success criteria (from their answers)
   - Boundaries (derived from constraints)
   - Context (knowledge level, clarity, constraints)

2. Store answers from the 5 questions in the contract

### Step 3: Analyze and Route (v7.24.0+: Hybrid Planning)

**NEW in v7.24.0:** Intelligent routing between native plan mode and octopus workflows.

#### Native Plan Mode Detection

First, check if native `EnterPlanMode` would be beneficial:

```javascript
// Conditions that favor native plan mode
const nativePlanModePreferred = (
  goal === "Build something" &&
  scope_clarity === "Clear requirements" &&
  knowledge_level === "Well-informed" &&
  !requires_multi_ai &&  // Simple single-phase planning
  !success.includes("Team alignment")  // No multi-perspective needs
)

if (nativePlanModePreferred) {
  // Suggest native plan mode
  AskUserQuestion({
    questions: [{
      question: "Would you like to use native plan mode or multi-AI orchestration?",
      header: "Planning Mode",
      multiSelect: false,
      options: [
        {
          label: "Native plan mode (Recommended)",
          description: "Fast, single-phase planning with Claude. Good for straightforward implementation plans."
        },
        {
          label: "Multi-AI orchestration",
          description: "Research with Codex + Gemini + Claude. Better for complex problems requiring diverse perspectives."
        }
      ]
    }]
  })
}
```

**When to use native EnterPlanMode:**
- ✅ Single-phase planning (just need a plan, no execution)
- ✅ Well-defined requirements
- ✅ Quick architectural decisions
- ✅ When context clearing after planning is OK

**When to use /octo:plan (octopus workflows):**
- ✅ Multi-AI orchestration (Codex + Gemini + Claude)
- ✅ Double Diamond 4-phase execution
- ✅ State needs to persist across sessions
- ✅ Complex intent capture with routing
- ✅ High-stakes decisions requiring multiple perspectives

#### Routing Logic (Octopus