How to Write CLAUDE.md: Three Types of Effective Instructions
How to write CLAUDE.md to give Claude Code project context, with before-and-after examples and the boundary between guidance and enforcement.
Designing Claude Code and Codex Collaboration
A guided series covering instruction files, shared rules, tool selection, handoffs, worktree state, and memory
6 postsSharing Claude Code and Codex Rules in shared/
How to centralize Claude Code and Codex policy in shared/, organize it by role, connect tool-specific references, and use synchronization checks to reduce missed updates.
Claude Code vs Codex: Discuss, Design, Implement, and Verify
How I choose between Claude Code and Codex in the same repository by comparing discussion, design, implementation, verification, and handoff work.
Choosing Between Claude Code and Codex, and Recording Work for Handoffs
How to hand work between Claude Code and Codex: record current state, completed work, remaining tasks, reasoning, and verification results, then resume in the next session.
How to Hand Off a Dirty Worktree Between AI Tools
A safe handoff process for uncommitted changes, separating what Codex Local, Worktree, and Cloud environments can see.
Codex Memories and AGENTS.md: Where to Keep Information and Rules
Learn which preferences and cautions belong in Codex Memories, which mandatory rules belong in AGENTS.md, and when to stop or review memory use and generation.