go-clean-arch

Use when executing a written implementation plan in the current session. Dispatches implementation subagents per task with dependency-aware wave parallelism, file-conflict checks, spec review, code-quality review, and validation.

Write E2E API tests using httpexpect and testcontainers for kfinops. Use when adding E2E tests, covering new API endpoints, or when user mentions E2E, end-to-end, integration testing, or API testing.

Execute implementation plans by dispatching subagents per task with dependency-aware parallel scheduling. Use when writing-plans or /go hands off a plan for same-session execution with wave-parallel subagents.

Use when writing or updating kfinops end-to-end HTTP API tests backed by httpexpect and testcontainers. Trigger for E2E/end-to-end/integration coverage of new or changed API endpoints, not for unit-only handler tests.

Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.

Explore user intent and turn ideas into fully formed designs through collaborative dialogue. Use before creating features, building components, adding functionality, or modifying behavior. Ensures requirements are clear before implementation begins.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, structural regressions, spaghetti growth, security risks, and proposes actionable improvements. Use when user asks for code review, PR review, or when /go pipeline reaches the review stage.

Find deepening opportunities in a codebase, informed by the project's architecture rules in .cursor/rules/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Write implementation plans with vertical slices, dependency graphs, interface contracts, and test-case descriptions. Use when you have a spec or requirements for a multi-step task, before touching code. The plan defines the skeleton (contracts + verification) and leaves implementation to the TDD implementer. Produces plans executable by subagent-driven-development.

Orchestrates an end-to-end workflow from requirements to implementation, review, and simplification. Use when user says /go or asks for a full design→plan→execute→review→simplify flow.

Enforce red-green-refactor TDD discipline for all implementation work. Use when implementing new features, fixing bugs, refactoring behavior, or when any production code needs to be written. Ensures no production code without a failing test first.

Use before creative or behavior-changing work: new features, components, workflows, functionality, or modifications. Explores user intent, constraints, alternatives, and design before planning or implementation.

Use before implementation code for any feature, bugfix, refactor, or behavior change. Enforces red-green-refactor: write and verify a failing test before production changes.

Use after requirements or design are understood and before coding a multi-step change. Creates concrete implementation plans with vertical slices, dependency graphs, file lists, TDD steps, and validation commands.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, structural regressions, spaghetti growth, security risks, and proposes actionable improvements. Use when user asks for code review, PR review, or when /go pipeline reaches the review stage.

Find deepening opportunities in a codebase, informed by the project's architecture rules. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.