boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Complete installation and configuration guide for integrating the spec-workflow MCP (Model Context Protocol) server with Claude Code to enable advanced task management and parallel execution capabilities.
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/spec-workflow-setupContext preview
What this command does when you run it.
Complete installation and configuration guide for integrating the spec-workflow MCP (Model Context Protocol) server with Claude Code to enable advanced task management and parallel execution capabilities.
allowed-tools: Bash, Read, Write, Edit, TodoWrite, WebFetch
Complete installation and configuration guide for integrating the spec-workflow MCP (Model Context Protocol) server with Claude Code to enable advanced task management and parallel execution capabilities.
The spec-workflow MCP server enables Claude to:
This command provides a comprehensive setup guide for the spec-workflow MCP server. When executed, follow these steps in order:
1. Check prerequisites (Node.js 18+, npm, Claude Code) 2. Choose an installation method (NPM, GitHub, or Claude Command Suite) 3. Configure the MCP server (using .mcp.json or global settings) 4. Create project-specific configuration files 5. Verify the installation 6. Test the connection with spec-workflow commands
The guide below provides detailed instructions for each step.
Before installation, ensure you have:
# Install globally npm install -g @pimzino/spec-workflow-mcp # Or install locally in your project npm install --save-dev @pimzino/spec-workflow-mcp
# Clone the repository git clone https://github.com/Pimzino/spec-workflow-mcp.git # Navigate to the directory cd spec-workflow-mcp # Install dependencies npm install # Build the server npm run build # Link globally for use npm link
# Navigate to Claude Command Suite directory cd Claude-Command-Suite # Run the spec-workflow installer ./scripts/install-spec-workflow-mcp.sh
Create a `.mcp.json` file in your project root. This is the simplest and most portable method:
**Location:** `.mcp.json` (in project root)
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", ".", "--AutoStartDashboard"],
"env": {}
}
}
}**Quick Setup:**
# Run this command in your project root
./scripts/add-spec-workflow-mcp.sh
# Or manually create the file
cat > .mcp.json << 'EOF'
{
"mcpServers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest", ".", "--AutoStartDashboard"],
"env": {}
}
}
}
EOF**Benefits of .mcp.json:**
Add the spec-workflow server to your global Claude configuration file:
**Location:** `~/.claude/settings.json`
{
"mcp": {
"servers": {
"spec-workflow": {
"command": "npx",
"args": ["-y", "@pimzino/spec-workflow-mcp@latest"],
"env": {
"SPEC_WORKFLOW_PROJECT_PATH": "${PROJECT_PATH}",
"SPEC_WORKFLOW_AUTO_SYNC": "true",
"SPEC_WORKFLOW_LOG_LEVEL": "info"
}
}
}
}
}Create a `.spec-workflow.json` file in your project root:
{
"version": "1.0.0",
"project": {
"name": "My Project",
"description": "Project using spec-workflow for task management"
},
"specifications": {
"directory": "./specifications",
"pattern": "**/*.spec.md",
"autoDiscovery": true
},
"tasks": {
"directory": "./tasks",
"statuses": ["todo", "in_progress", "review", "qa", "completed", "blocked"],
"defaultStatus": "todo",
"trackDependencies": true
},
"agents": {
"maxParallel": 4,
"autoAssign": true,
"conflictResolution": "abort"
},
"sync": {
"github": {
"enabled": false,
"repository": "owner/repo",
"labelMapping": {
"todo": "task:todo",
"in_progress": "task:in-progress",
"completed": "task:done"
}
},
"linear": {
"enabled": false,
"teamId": "TEAM_ID",
"projectId": "PROJECT_ID"
}
}
}Set up environment variables for the MCP server:
# Add to ~/.bashrc, ~/.zshrc, or equivalent export SPEC_WORKFLOW_PROJECT_PATH="$HOME/projects" export SPEC_WORKFLOW_AUTO_SYNC="true" export SPEC_WORKFLOW_LOG_LEVEL="info" export SPEC_WORKFLOW_CACHE_DIR="$HOME/.cache/spec-workflow"
After configuration, verify the connection:
# Start Claude Code claude code # In Claude, test the connection /spec-workflow:test-connection
Expected output:
✅ Spec-Workflow MCP Server Connected Version: 1.0.0 Project: My Project Specifications Found: 5 Tasks Available: 23 Status: Ready
# In Claude Code /spec-workflow:list-specs
# In Claude Code /spec-workflow:task-status
# List all tasks in a specification /spec-workflow:list-tasks --spec-name user-authentication # Create a new task /spec-workflow:create-task --spec-name payment-integration --description "Implement Stripe webhook handling" # Update task status /spec-workflow:update-task --task-id TASK-001 --status in_progress # Assign task to agent /spec-workflow:assign-task --task-id TASK-001 --agent typescript-pro
# Execute tas
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles:…