.Codex

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

Test-Driven Development workflow. Use for ALL code changes - features, bug fixes, refactoring. TDD is non-negotiable.

Run dependency security audit using pip-audit. Use when checking for known vulnerabilities in project dependencies.

Check code quality without making changes — lint, format, type, and security checks. Use when you want to inspect issues before fixing them.

Delegate to OpenAI Codex CLI when: (1) user explicitly requests it (codex에게 맡겨줘, codex로 해줘, 외주화해줘, codex 실행해줘, codex 리뷰 돌려줘), OR (2) the task requires autonomous repo-scale execution — writing multiple test files, file-level refactoring across many files, bulk edits (type hints, formatting, comments across a directory), or code review with a clear done condition. Do NOT delegate: design/architecture decisions, small edits (under ~20 lines), explanation-only requests, or tasks where Claude needs to reason about context first.

Testing patterns for behavior-driven tests. Use when writing tests or test factories.

Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new work, or marking tasks complete. Requires explicit arguments: worklog [done|doing|todo] [description].

Auto-fix lint and formatting issues in Python code using ruff. Use when you want to apply automatic code fixes. Does not fix type errors or security issues.

Planning work in small, known-good increments. Use when starting significant work or breaking down complex tasks.

Refactoring assessment and patterns. Use after tests pass (GREEN phase) to assess improvement opportunities.

Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 for content that lives outside learn.microsoft.com.

Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.

Expert assistant for developing Model Context Protocol (MCP) servers in Python. Use when creating, debugging, or optimizing MCP servers with FastMCP, tools, resources, and prompts.

Python coding conventions and guidelines including PEP 8, type hints, docstrings, and testing standards. Automatically applied when working with Python files.

Evaluates test quality using Dave Farley's 8 properties. Use when reviewing tests, assessing test suite quality, or analyzing test effectiveness against TDD best practices.