moai-workflow-thinking

Use Sequential Thinking MCP when:

• Breaking down complex problems into steps
• Planning and design with room for revision
• Architecture decisions affect 3+ files
• Technology selection between multiple options
• Performance vs maintainability trade-offs
• Breaking changes under consideration
• Multiple approaches exist to solve the same problem
• Repetitive errors occur

Required Parameters:

• thought (string): Current thinking step content
• nextThoughtNeeded (boolean): Whether another step is needed
• thoughtNumber (integer): Current thought number (starts from 1)
• totalThoughts (integer): Estimated total thoughts needed

Optional Parameters:

• isRevision (boolean): Whether this revises previous thinking
• revisesThought (integer): Which thought is being reconsidered
• branchFromThought (integer): Branching point for alternatives
• branchId (string): Branch identifier
• needsMoreThoughts (boolean): If more thoughts needed beyond estimate

Step 1 - Initial Analysis:

```

thought: "Analyzing the problem: [describe problem]"

nextThoughtNeeded: true

thoughtNumber: 1

totalThoughts: 5

```

Step 2 - Decomposition:

```

thought: "Breaking down: [sub-problems]"

nextThoughtNeeded: true

thoughtNumber: 2

totalThoughts: 5

```

Step 3 - Revision (if needed):

```

thought: "Revising thought 2: [correction]"

isRevision: true

revisesThought: 2

thoughtNumber: 3

totalThoughts: 5

nextThoughtNeeded: true

```

Final Step - Conclusion:

```

thought: "Conclusion: [final answer]"

thoughtNumber: 5

totalThoughts: 5

nextThoughtNeeded: false

```

Enhanced analysis mode activated by --ultrathink flag.

Activation:

```

"Implement authentication system --ultrathink"

"Refactor the API layer --ultrathink"

```

Process:

1. Request Analysis: Identify core task, detect keywords, recognize complexity
2. Sequential Thinking: Begin structured reasoning
3. Execution Planning: Map subtasks to agents, identify parallel opportunities
4. Execution: Launch agents, integrate results

UltraThink Parameters:

Initial Analysis:

```

thought: "Analyzing user request: [content]"

nextThoughtNeeded: true

thoughtNumber: 1

totalThoughts: [estimate]

```

Subtask Decomposition:

```

thought: "Breaking down: 1) [task1] 2) [task2] 3) [task3]"

nextThoughtNeeded: true

thoughtNumber: 2

```

Agent Mapping:

```

thought: "Mapping: [task1] → expert-backend, [task2] → expert-frontend"

nextThoughtNeeded: true

thoughtNumber: 3

```

Execution Strategy:

```

thought: "Strategy: [tasks1,2] parallel, [task3] depends on [task1]"

nextThoughtNeeded: true

thoughtNumber: 4

```

Final Plan:

```

thought: "Plan: Launch [agents] in parallel, then [agent]"

nextThoughtNeeded: false

```

UltraThink is ideal for:

• Complex multi-domain tasks (backend + frontend + testing)
• Architecture decisions affecting multiple files
• Performance optimization requiring analysis
• Security review needs
• Refactoring with behavior preservation

Benefits:

• Structured decomposition of complex problems
• Explicit agent-task mapping with justification
• Identification of parallel execution opportunities
• Context maintenance throughout reasoning
• Revision capability when approaches need adjustment

1. Start with reasonable totalThoughts estimate
2. Use isRevision when correcting previous thoughts
3. Maintain thoughtNumber sequence
4. Set nextThoughtNeeded to false only when complete
5. Use branching for exploring alternatives