/plan

Plan Command

This command creates a comprehensive implementation plan before writing any code.

Run inline by default. Do not call the Task tool or any subagent by default. This keeps /plan usable from plugin installs that ship commands without agent files.

What This Command Does

1. Restate Requirements - Clarify what needs to be built
2. Identify Risks - Surface potential issues and blockers
3. Create Step Plan - Break down implementation into phases
4. Wait for Confirmation - MUST receive user approval before proceeding

When to Use

Use /plan when:

• Starting a new feature
• Making significant architectural changes
• Working on complex refactoring
• Multiple files/components will be affected
• Requirements are unclear or ambiguous

How It Works

The assistant will:

1. Analyze the request and restate requirements in clear terms
2. Break down into phases with specific, actionable steps
3. Identify dependencies between components
4. Assess risks and potential blockers
5. Estimate complexity (High/Medium/Low)
6. Present the plan and WAIT for your explicit confirmation

Example Usage

User: /plan I need to add real-time notifications when markets resolve

Assistant:
# Implementation Plan: Real-Time Market Resolution Notifications

## Requirements Restatement
- Send notifications to users when markets they're watching resolve
- Support multiple notification channels (in-app, email, webhook)
- Ensure notifications are delivered reliably
- Include market outcome and user's position result

## Implementation Phases

### Phase 1: Database Schema
- Add notifications table with columns: id, user_id, market_id, type, status, created_at
- Add user_notification_preferences table for channel preferences
- Create indexes on user_id and market_id for performance

### Phase 2: Notification Service
- Create notification service in lib/notifications.ts
- Implement notification queue using BullMQ/Redis
- Add retry logic for failed deliveries
- Create notification templates

### Phase 3: Integration Points
- Hook into market resolution logic (when status changes to "resolved")
- Query all users with positions in market
- Enqueue notifications for each user

### Phase 4: Frontend Components
- Create NotificationBell component in header
- Add NotificationList modal
- Implement real-time updates via Supabase subscriptions
- Add notification preferences page

## Dependencies
- Redis (for queue)
- Email service (SendGrid/Resend)
- Supabase real-time subscriptions

## Risks
- HIGH: Email deliverability (SPF/DKIM required)
- MEDIUM: Performance with 1000+ users per market
- MEDIUM: Notification spam if markets resolve frequently
- LOW: Real-time subscription overhead

## Estimated Complexity: MEDIUM
- Backend: 4-6 hours
- Frontend: 3-4 hours
- Testing: 2-3 hours
- Total: 9-13 hours

**WAITING FOR CONFIRMATION**: Proceed with this plan? (yes/no/modify)

Important Notes

CRITICAL: This command will NOT write any code until you explicitly confirm the plan with "yes" or "proceed" or similar affirmative response.

If you want changes, respond with:

• "modify: [your changes]"
• "different approach: [alternative]"
• "skip phase 2 and do phase 3 first"

Integration with Other Commands

After planning:

• Use the tdd-workflow skill to implement with test-driven development
• Use /build-fix if build errors occur
• Use /code-review to review completed implementation

Need deeper planning? Use /prp-plan for artifact-producing planning with PRD integration, codebase analysis, and pattern extraction. Use /prp-implement to execute those plans with rigorous validation loops.

Optional Planner Agent

ECC also provides a planner agent for manual installs that include agent files. Use it only when the local runtime already exposes that subagent and the user explicitly asks you to delegate planning.

If the planner subagent is unavailable, continue planning inline instead of surfacing an "Agent type 'planner' not found" error.

For manual installs, the source file lives at: agents/planner.md