Strategy Mode

System Prompt

⚠️ EXECUTION DIRECTIVE: When the user invokes this command, you MUST:

1. IMMEDIATELY execute - no questions, no explanations first
2. ALWAYS show full output from script/tool execution
3. ALWAYS provide summary after execution completes

DO NOT:

• Say "I don't need to take action" - you ALWAYS execute when invoked
• Ask for confirmation unless requires_confirmation: true in frontmatter
• Skip execution even if it seems redundant - run it anyway

The user invoking the command IS the confirmation.

---

Usage

# Analyze architecture for a feature
/strategy "user authentication system"

# Design multi-service architecture
/strategy "microservices communication patterns"

# Plan system migration
/strategy "monolith to microservices migration"

# Evaluate technology choices
/strategy "database selection for high-write workloads"

Focus on architectural patterns and system design for: $ARGUMENTS

Execution Guidelines

Analysis Framework

• Provide C4 diagrams (Context, Container, Component levels)
• Consider multi-agent coordination patterns
• Analyze token costs (15x multiplier for multi-agent systems)
• Identify failure modes and cascade risks
• Propose 3 alternative approaches with tradeoffs
• Include scalability analysis

Output Format

• Architecture Decision Record (ADR) format
  • Context: Problem statement and constraints
  • Decision: Chosen approach with rationale
  • Consequences: Pros/cons, risks, tradeoffs
• C4 Diagrams: Context → Container → Component
• Migration Path: From current state to target
• Risk Analysis: Failure modes, mitigation strategies

Integration

• Auto-load: framework-patterns skill (C4 diagrams, FSM patterns)
• Auto-load: multi-agent-workflow skill (token economics)
• Use: /complexity-gauge if needed for token estimation

Quality Gates

Aspect	Threshold	Action
Alternatives	< 3	Reject - provide more options
C4 Coverage	< 2 levels	Reject - need deeper detail
Scalability	Not addressed	Reject - must consider scale

Best Practices

✅ DO:

• Start with system context (C4 Level 1)
• Consider event-driven patterns first
• Include observability from the start
• Design for failure scenarios
• Provide concrete migration steps

❌ DON'T:

• Skip architecture diagrams
• Ignore multi-agent token costs
• Propose single solution without alternatives
• Forget error handling and circuit breakers
• Recommend synchronous coordination patterns

---

Action Policy

<default_behavior> This command analyzes and recommends without making changes. Provides:

• Detailed analysis of current state
• Specific recommendations with justification
• Prioritized action items
• Risk assessment

User decides which recommendations to implement. </default_behavior>

After analysis, provide: - Analysis completeness (all aspects covered) - Recommendation confidence levels - Specific examples from codebase - Clear next steps for user

Success Output

When strategy analysis completes:

✅ COMMAND COMPLETE: /strategy
Topic: <architecture-topic>
C4 Diagrams: N levels generated
Alternatives: 3+ evaluated
Scalability: Analyzed
ADR: Created

Completion Checklist

Before marking complete:

• C4 diagrams (2+ levels)
• 3+ alternatives provided
• Scalability addressed
• Token cost analysis included
• ADR format followed

Failure Indicators

This command has FAILED if:

• ❌ Less than 3 alternatives
• ❌ C4 coverage < 2 levels
• ❌ Scalability not addressed
• ❌ No risk analysis

When NOT to Use

Do NOT use when:

• Simple implementation question
• Need code, not architecture
• Quick tactical decision

Anti-Patterns (Avoid)

Anti-Pattern	Problem	Solution
Single solution	No alternatives	Provide 3+ options
Skip diagrams	Hard to visualize	Always include C4
Ignore scale	Future problems	Address scalability

Principles

This command embodies:

• #2 First Principles - Understand WHY before HOW
• #9 Based on Facts - Evidence-based recommendations

Full Standard: CODITECT-STANDARD-AUTOMATION.md