Tag: Claude Code
About Claude Code
productClaude Code is Anthropic’s command-line agent harness, designed around tight model-and-harness co-design. It’s the closest thing to a “default” harness for Anthropic-model users and the reference implementation for the Skills system. Coverage on this tag follows releases, viral threads, and the long-running debate over how much vendor-coupling is the right amount.
-
Claude Code's new Skills system is quietly rewriting how devs ship with agents
Reusable, versioned agent behaviors are turning ad-hoc prompts into shared infrastructure — and the rest of the harness ecosystem is watching.
-
Inside the harness wars: how Claude Code, Codex, Hermes, and OpenClaw are redrawing the agent stack
Four contenders, four philosophies, two completely different problem statements. We talked to people on all four sides about what they're actually competing on — and where they're not competing at all.