Engineering guides and deep dives on Harness - short how-tos and long-form breakdowns.
Microsoft Execution Containers 1.0 enforces one JSON sandbox policy outside Codex and Copilot. Its denial log can draft that policy, but only on Windows, and --audit turns containment off.
I ran claude plugin eval on obra/superpowers vs no plugin: it changed how Claude worked on 3 of 7 tasks, improved the result on 1, and cost 1.33x per task.
On the adversarial task its line-36 rule existed to prevent, a 129-instruction CLAUDE.md gave the same one-word reply as a harness with no instructions.
A minimal Claude Code harness in ten files: a lean CLAUDE.md, a definition-of-done loop, read-only subagents, and credential deny rules. One npx install.
Google's 2026 SDLC whitepaper draws the line between vibe coding and agentic engineering at verification, not AI use - and the harness decides your side.