Fitness Function Design
Design quantifiable metrics to measure architecture health and automatically enforce quality standards.
Context
You are designing fitness functions to measure architectural quality. Create metrics for coupling, modularity, scalability, performance. Automate checks in CI/CD for continuous feedback.
Domain Context
Based on evolutionary architecture and fitness function research (Thoughtworks):
- Coupling Metrics: Layer violations, cyclic dependencies, test isolation
- Modularity Metrics: Module fan-in/fan-out, cohesion, abstract instability
- Scalability Metrics: Throughput (RPS), latency (p95, p99), resource utilization
- Security Metrics: Secrets in code, dependency vulnerabilities, known security patterns
- Code Quality Metrics: Complexity (cyclomatic), duplication, test coverage
Instructions
Identify Key Quality Attributes: What matters most? Scalability? Security? Testability? Maintainability? Pick 3-4.
Define Metrics for Each Attribute: Scalability: p99 latency < 200ms, peak RPS capacity. Security: zero secrets in code, all dependencies scanned. Testability: > 80% test coverage, no untestable dependencies.
Set Thresholds: Below threshold: pass. Above: fail (blocks merge). Make thresholds achievable but stretch. Too strict: teams bypass. Too loose: no effect.
Automate Checks: Integrate into CI/CD. Run on every PR. Parse test coverage reports, dependency scanners, performance benchmarks. Fail PR if fitness functions breach.
Monitor and Adjust: Track metrics over time. Are they trending right? Do developers understand why they matter? Adjust thresholds based on feedback and organizational priorities.
Anti-Patterns
- Too Many Fitness Functions: 50 metrics in CI/CD. Result: long builds, false positives, ignored. Guard: 5-10 core metrics max. Automate what matters; remove noise.
- Fitness Functions Without Context: "Cyclomatic complexity > 10 fails". Developer doesn't understand why. Result: frustrated, rules bypassed. Guard: Document rationale; train teams; explain tradeoffs.
- Static Thresholds: Set once, never changed. Organization evolves, thresholds stale. Result: metrics become irrelevant. Guard: Review quarterly; adjust based on trends and priorities.
- Metrics Without Action: Fitness functions fail but no one addresses. Result: technical debt accumulates. Guard: Failed checks require action; track and fix root causes.
Further Reading
- Evolutionary Architecture by Rebecca Parsons, Neal Ford, Patrick Kua — fitness function concepts
- Building Microservices by Sam Newman — quality metrics for distributed systems
- Accelerate by Nicole Forsgren — DORA metrics for deployment performance
1---2name: fitness-function-design3description: Design metrics that measure architecture health (coupling, modularity, scalability). Automate fitness function checks in CI/CD. Use when establishing quality gates or measuring architectural degradation.4---56# Fitness Function Design78Design quantifiable metrics to measure architecture health and automatically enforce quality standards.910## Context1112You are designing fitness functions to measure architectural quality. Create metrics for coupling, modularity, scalability, performance. Automate checks in CI/CD for continuous feedback.1314## Domain Context1516Based on evolutionary architecture and fitness function research (Thoughtworks):1718- **Coupling Metrics**: Layer violations, cyclic dependencies, test isolation19- **Modularity Metrics**: Module fan-in/fan-out, cohesion, abstract instability20- **Scalability Metrics**: Throughput (RPS), latency (p95, p99), resource utilization21- **Security Metrics**: Secrets in code, dependency vulnerabilities, known security patterns22- **Code Quality Metrics**: Complexity (cyclomatic), duplication, test coverage2324## Instructions25261. **Identify Key Quality Attributes**: What matters most? Scalability? Security? Testability? Maintainability? Pick 3-4.27282. **Define Metrics for Each Attribute**: Scalability: p99 latency < 200ms, peak RPS capacity. Security: zero secrets in code, all dependencies scanned. Testability: > 80% test coverage, no untestable dependencies.29303. **Set Thresholds**: Below threshold: pass. Above: fail (blocks merge). Make thresholds achievable but stretch. Too strict: teams bypass. Too loose: no effect.31324. **Automate Checks**: Integrate into CI/CD. Run on every PR. Parse test coverage reports, dependency scanners, performance benchmarks. Fail PR if fitness functions breach.33345. **Monitor and Adjust**: Track metrics over time. Are they trending right? Do developers understand why they matter? Adjust thresholds based on feedback and organizational priorities.3536## Anti-Patterns3738- **Too Many Fitness Functions**: 50 metrics in CI/CD. Result: long builds, false positives, ignored. **Guard**: 5-10 core metrics max. Automate what matters; remove noise.39- **Fitness Functions Without Context**: "Cyclomatic complexity > 10 fails". Developer doesn't understand why. Result: frustrated, rules bypassed. **Guard**: Document rationale; train teams; explain tradeoffs.40- **Static Thresholds**: Set once, never changed. Organization evolves, thresholds stale. Result: metrics become irrelevant. **Guard**: Review quarterly; adjust based on trends and priorities.41- **Metrics Without Action**: Fitness functions fail but no one addresses. Result: technical debt accumulates. **Guard**: Failed checks require action; track and fix root causes.4243## Further Reading4445- _Evolutionary Architecture_ by Rebecca Parsons, Neal Ford, Patrick Kua — fitness function concepts46- _Building Microservices_ by Sam Newman — quality metrics for distributed systems47- _Accelerate_ by Nicole Forsgren — DORA metrics for deployment performance
sethdford