Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Designing One AI-SDLC Workflow for Claude Code and Codex

AI summary

A tutorial maps six coding-agent primitives—AGENTS.md/CLAUDE.md, Skill, Subagent, Hook, MCP, and permissions with sandboxes—to the five stages of AI-driven software development. It proposes storing roles, skills, and hooks in neutral source files, then generating host-specific projections for Claude Code and Codex. The article also describes differences in read-only subagents, hook approval, and skill directories, alongside preflight and log-based verification.

In-depth insight

The neutral-source and projection approach gives teams a concrete way to maintain one AI-SDLC workflow across two coding-agent hosts while making unsupported capabilities and trust-dependent execution explicit.

Claude Code 和 Codex 都提供六种可以直接拿来搭流程的能力:AGENTS.md/CLAUDE.md、Skill、Subagent、Hook、MCP、权限与沙箱。

本篇讲三件事:

  • 六种能力各自的作用和适用场景;
  • 我们在 AI-SDLC 的五个阶段里分别用它们做了什么;
  • 同一套工程怎样同时支持 Claude Code 和 Codex。

文中的平台行为以两边截至 2026 年 11 月的官方文档为准。

Agent = Model + Harness:Harness 管的是上下文窗口

Harness 的核心工作是管理每一轮的上下文窗口

#Claude Code#Codex#Anthropic#OpenAI#Agent Skills#Model Context Protocol

Original · 14 min readRead the original
Group chat

No comments yet. Start the conversation.