According to @bcherny on X, developers can create custom Claude Code agents by defining agent configurations in the .claude/agents directory and invoking them with the claude --agent flag, enabling tailored system prompts and toolchains for coding workflows; as reported by Anthropic’s official docs, sub-agents support specialized behaviors, tool access, and scoped prompts for tasks like refactoring, test generation, and repo triage, offering teams a repeatable way to standardize prompts across projects; according to code.claude.com documentation, organizations can compose multiple sub-agents, assign permissions, and streamline developer operations with reusable agent templates, which can reduce context-switching and improve code review throughput for practical business impact.