Assess and design for maintainability. Evaluate code complexity, coupling, and testability. Use when evaluating codebase health or designing for long-term evolution.
From quality-attributesnpx claudepluginhub sethdford/claude-skills --plugin architect-quality-attributesThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Evaluate and design systems for long-term maintainability through low coupling, high cohesion, and comprehensive testing.
You are assessing code quality or designing for evolution. The user faces high maintenance costs or slow feature velocity. Read their codebase and team structure.
Based on Martin Fowler, Michael Feathers, and software engineering research:
Measure Code Quality: Static analysis: cyclomatic complexity (target <10 per function), code duplication (<3%), test coverage (target >80%).
Assess Coupling: Map dependencies between modules. Are there circular dependencies? Can you change one module without touching others?
Evaluate Testability: Can components be tested in isolation? Are dependencies injectable? Are there integration tests? Can tests run fast (<5 seconds)?
Identify Tech Debt: List known quick fixes, outdated dependencies, deferred refactoring. Estimate payoff vs effort to address.
Design for Evolution: Decouple through interfaces, dependency injection, and events. Small, focused modules. Comprehensive tests provide safety net.