boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Model world constraints with assumption validation, dependency mapping, and scenario boundary definition.
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/constraint-modelerContext preview
What this command does when you run it.
Model world constraints with assumption validation, dependency mapping, and scenario boundary definition.
Model world constraints with assumption validation, dependency mapping, and scenario boundary definition.
You are tasked with systematically modeling the constraints that govern your decision environment to create accurate simulations and scenarios. Follow this approach: **$ARGUMENTS**
**Critical Constraint Context Validation:**
**If context is unclear, guide systematically:**
Missing Domain Context: "I need to understand what you're modeling constraints for: - Business Domain: Market constraints, competitive dynamics, regulatory environment - Technical Domain: System limitations, performance bounds, technology constraints - Operational Domain: Resource constraints, process limitations, capacity bounds - Financial Domain: Budget constraints, investment limitations, economic factors Examples: - 'SaaS business operating in regulated healthcare market' - 'Manufacturing system with supply chain and quality constraints' - 'Software architecture with performance and scalability requirements'" Missing Constraint Types: "What types of constraints are most relevant to your decisions? - Hard Constraints: Absolute limits that cannot be violated - Soft Constraints: Preferences and trade-offs that can be managed - Regulatory Constraints: Legal and compliance requirements - Resource Constraints: Budget, time, and capacity limitations - Market Constraints: Customer behavior and competitive dynamics"
**Systematically categorize and structure constraints:**
Physical/Natural Constraints: - Laws of physics and natural limitations - Geographic and spatial boundaries - Time and temporal restrictions - Resource scarcity and finite capacity Regulatory/Legal Constraints: - Compliance requirements and legal mandates - Industry standards and certification requirements - Contractual obligations and agreements - Intellectual property and licensing restrictions Technical Constraints: - System capacity and performance limits - Technology compatibility and integration requirements - Security and privacy constraints - Infrastructure limitations and dependencies
Economic Constraints: - Budget limitations and financial resources - Cost optimization and efficiency targets - Investment return requirements and payback periods - Market pricing and competitive pressure Organizational Constraints: - Team capacity and skill limitations - Cultural and change management factors - Decision-making processes and approval cycles - Risk tolerance and strategic priorities Market Constraints: - Customer preferences and behavior patterns - Competitive dynamics and response patterns - Market timing and seasonal factors - Distribution channel limitations and requirements
Evolutionary Constraints: - Technology advancement and obsolescence cycles - Market maturation and customer evolution - Regulatory changes and policy shifts - Competitive landscape evolution Cyclical Constraints: - Seasonal business patterns and market cycles - Economic cycles and market conditions - Budget cycles and resource allocation patterns - Technology refresh and upgrade cycles
**Create comprehensive constraint relationship models:**
Constraint Relationship Analysis: Primary Constraints → Secondary Effects: - Budget Limitation → Team size → Development capacity → Feature scope - Regulatory Requirement → Compliance process → Timeline extension → Market timing - Technical Constraint → Architecture choice → Scalability → Growth potential Constraint Conflicts and Trade-offs: - Speed vs. Quality: Time constraint vs. quality constraint - Cost vs. Capability: Budget constraint vs. feature constraint - Security vs. Usability: Security constraint vs. user experience constraint - Scale vs. Simplicity: Growth constraint vs. complexity constraint Constraint Dependencies: - Sequential: Constraint A must be satisfied before addressing Constraint B - Conditional: Constraint A applies only if Condition X is true - Mutual: Constraints A and B reinforce or conflict with each other - Hierarchical: Constraint A contains or encompasses Constraint B
**Systematically test and validate constraint assumptions:**
Constraint Assumption Template: Constraint: [Name and description] Assumption: [What we believe to be true about this constraint] Source: [Where this assumption comes from] Confidence Level: [1-10 scale with justification] Impact if Wrong: [What happens if assumption is incorrect] Validation Method: [How to test this assumption] Update Frequency: [How often to re-validate] Example: Constraint: "Engineering team capacity" Assumption: "Team can deliver 10 story points per sprint" Source: "Historical velocity data from last 6 sprints" Confidence Level: "8 - consistent recent data but team composition changing" Impact if Wrong: "Project timeline delays, scope reduction needed" Validation Method: "Track actual velocity, monitor team changes
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:…