Constraint Modeler Processor

Systematically model, validate, and optimize constraints across business, technical, and operational domains to identify feasible solution spaces and bottleneck resolution paths.

When to Use This Command

Run this command when...

• You need to map out all constraints affecting a system design, resource allocation, or operational process before implementation begins
• You want to identify which constraints are binding versus slack and determine the highest-leverage relaxation points
• Your project has interdependent technical and business limitations that must be modeled together to find a feasible solution

Do NOT use this command when...

• You have a single simple constraint that can be checked with a quick calculation
• You need real-time constraint satisfaction solving with a dedicated optimization engine

Quick Start

Copy
# .claude/commands/constraint-modeler-processor.md
# Model system constraints
Model constraints for: $ARGUMENTS

Copy
# Run the command
claude "constraint-modeler-processor API rate limits with 10k concurrent users and 99.9% uptime SLA"

Expected output:
- Constraint taxonomy (technical, operational, financial)
- Binding vs. slack constraint classification
- Feasibility analysis with solution space boundaries
- Bottleneck identification and relaxation recommendations
- Constraint interaction matrix

Core Concepts

Concept	Description
Constraint Taxonomy	Categorization into hard (non-negotiable) and soft (flexible) constraints
Feasibility Space	The region of solutions satisfying all active constraints simultaneously
Binding Analysis	Identifies which constraints actively limit the optimal solution
Relaxation Path	Ordered sequence of constraint adjustments yielding maximum improvement
Interaction Matrix	Maps how relaxing one constraint affects others in the system

Constraint Modeling Flow:

  Inputs (Domain, Limits, Dependencies)
       |
  [Classify Constraints]
       |
  +----+----+
  |         |
 Hard     Soft
  |         |
  [Map Interactions]
       |
  [Find Feasible Space]
       |
  [Identify Binding]
       |
  Relaxation Plan

Configuration

Parameter	Default	Description
Domain Scope	Auto-detect	Business, technical, operational, or financial constraint domain
Constraint Sources	Docs + config	Files scanned for existing system limitations
Optimization Goal	Maximize feasibility	Whether to maximize throughput, minimize cost, or balance
Sensitivity Level	Medium	Granularity of constraint interaction analysis
Output Detail	Full report	Summary, detailed, or full report with interaction matrix

Best Practices

1. Enumerate constraints explicitly -- list known constraints in your arguments rather than relying on inference. State "budget 500k, team of 4, deadline March" for precise modeling
2. Distinguish hard from soft -- indicate which constraints are non-negotiable versus flexible so the model can focus relaxation analysis on actionable items
3. Include units and thresholds -- constraints like "latency under 200ms" are far more useful than "low latency" for feasibility analysis
4. Model in layers -- start with technical constraints, then layer in business and operational ones to build understanding incrementally
5. Revisit after changes -- re-run the modeler whenever a constraint changes because relaxing one binding constraint often reveals the next bottleneck

Common Issues

1. Feasible space appears empty -- this means your constraints are collectively unsatisfiable. Review hard constraints for any that can be reclassified as soft, or adjust thresholds
2. Too many constraints listed -- the model may surface implicit constraints you did not consider. Review the taxonomy to confirm each is real and relevant to your domain
3. Interaction effects missed -- provide more context about system dependencies. Constraints on separate subsystems that share resources must be modeled with their coupling points