How to write the code review SKILL.md your team actually needsPrompts such as "review this code thoroughly" hide several choices because nobody has defined what "thorough" means. It might mean runtime behavior, architecture, security, product intent, or all of tAug 4 · 13 min readsingular.hashnode.dev
Unifying Codex, OpenCode, and Pi in Remote Sandboxes with ACPImagine Codex needs to inspect a repository in a remote VM. It needs to read that copy, run commands there, ask for permission, and send updates back to your app. That is a session, not a shell commanAug 3 · 6 min readsingular.hashnode.dev
What if we could compose AI agents like reusable components?One agent reviews correctness. Another plans the tests. Their outputs flow into a third agent that produces one release recommendation. That is agent composition: small specialists, explicit datafloAug 2 · 4 min readsingular.hashnode.dev
Introducing: AML - Agent Markup LanguageOur first agent workflows were easy to start. Then we added another agent, a tool, a follow-up turn, a sandbox, and somewhere to keep files between runs. The code still worked, but understanding the w1Aug 1 · 5 min readsingular.hashnode.dev
