implement-test

Automating test implementation from spec and test case definitions involves delegating the actual test code generation to sub-agents while a main agent orchestrates the workflow. This enforces project rules like typecheck, lint, and end-to-end test execution across domain, adapter, and use-case layers.

Sub-agent orchestration for QA review delegates specific test implementation tasks to sub-agents while the main agent tracks progress and enforces quality. It runs a retry loop up to three times for failing checks, ensuring comprehensive coverage across domain logic, adapters, and use-cases.

Before delegating test implementation to sub-agents, you need existing spec or test case definitions and a CLAUDE.md file containing project rules. These prerequisites allow the orchestration agent to enforce typecheck, lint, and end-to-end test execution requirements automatically.

Yes, you can enforce typecheck and lint rules during automated test implementation by defining them in a CLAUDE.md file. The orchestrating agent reads these project rules and applies them within a retry loop that attempts to fix failures up to three times.

The best way to ensure comprehensive test coverage across domain, adapters, and use-cases is orchestrating sub-agents to implement tests based on existing spec definitions. This approach systematically validates multiple architectural layers while automatically enforcing end-to-end test execution.

Automated test implementation may fail end-to-end tests due to incomplete spec coverage or linting errors. The orchestration workflow handles this by running a retry loop up to three times, providing progress updates while the sub-agents attempt to fix the failing test implementation.