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.

According to @bcherny, developers can create custom agents in Claude Code by adding .md files to .claude/agents, enabling per-agent names, colors, tool sets, pre-allowed or pre-disallowed tools, permission modes, and model selection; developers can also set a default agent via the agent field in settings.json or the --agent flag, as reported by the tweet and Claude Code docs. According to code.claude.com, running /agents provides an entry point to manage sub-agents and learn more about capabilities, which streamlines workflow routing and role specialization for coding tasks. According to the Claude Code documentation, this supports enterprise use cases like policy-constrained code changes, safer tool invocation, and faster task handoffs within developer teams.