Codex

Best practices Strong first use : Context and Prompts Clear prompting makes results more reliable A good default is to include four things in your prompt: Goal: What are you trying to change or build? Context: Which files, folders, docs, examples, or errors matter for this task? You can @ mention certain files as context. Constraints: What standards, architecture, safety requirements, or conventions should Codex follow? Done when: What should be true before the task is complete, such as tests passing, behavior changing, or a bug no longer reproducing? it is similar to Claude Code Best practices ...

OpenAI是如何使用Codex: 用例1:代码理解 识别核心逻辑;梳理服务和板块之间的关系;追踪数据在系统中的流转;识别架构模式和文档确实的部分 用例2:重构和迁移: 跨文件执行修改操作;拆分模块 用例3:性能优化: 用于识别并解决性能瓶颈问题 ...

Personalize GPT set preference and carry useful context across chats: Choose a personality: Friendly, pragmatic,or None Add custom instructions: In your global AGENTS.md Carry context forward with memories: Memories are separate from required project guidance. Keep instructions that must always apply in AGENTS.md or checked-in project documentation. Add recent activity with Computer History Review what Computer History includes before enabling it Manage personalization: pen Settings to update your personality, custom instructions, memories, and other available personalization controls. See ChatGPT desktop app settings for an overview of everyday preferences.