Council MCP Procedures

Invoke with /tzurot-council-mcp when you need external AI consultation.

When to Consult Council

Always Use For

• Major Refactorings (>500 lines)
• Before Completing Major PRs
• When Thinking “This seems unnecessary” – STOP! Consult before removing code.
• Structured Debugging

Don’t Use For

• Questions answered by existing docs/skills
• Obvious code issues (typos, syntax errors)
• Small style preferences

Debugging Procedure

mcp__council__debug({
  error_message: 'Memory leak in BullMQ workers',
  code_context: 'Workers OOM after 2 hours',
  previous_attempts: ['Checked event listeners', 'Reviewed Redis connections'],
});

Code Review Procedure

mcp__council__code_review({
  code: changes,
  focus: 'behavior preservation, edge cases',
  language: 'typescript',
});

Refactoring Plan Procedure

mcp__council__refactor({
  code: myCode,
  goal: 'reduce_complexity', // extract_method, simplify_logic, improve_naming, etc.
  language: 'typescript',
});

Brainstorming Procedure

mcp__council__brainstorm({
  topic: 'Risks in refactoring PersonalityService',
  constraints: 'Must maintain exact functionality',
});

Model Selection

// Get recommendation
mcp__council__recommend_model({ task: 'code_review' });

// Specify per-call
mcp__council__code_review({
  code: myCode,
  model: 'anthropic/claude-3.5-sonnet',
});

Multi-Turn Conversations

// Start session
const { session_id } = await mcp__council__start_conversation({
  model: 'deepseek/deepseek-r1',
  system_prompt: 'You are a TypeScript architecture expert',
  initial_message: 'Review this service design...',
});

// Continue
await mcp__council__continue_conversation({
  session_id,
  message: 'What about the error handling?',
});

// End and summarize
await mcp__council__end_conversation({
  session_id,
  summarize: true,
});

When Council and Claude Disagree

Resolution hierarchy:

1. Project guidelines (CLAUDE.md, rules)
2. Existing codebase patterns
3. Technical correctness
4. User preference

Available Tools