Unverified50% confidenceFactExact time
Claude's sub-agents are defined via options.agents, and the background=False field is used to make the main agent wait for the sub-agent to return before the main agent composes its reply.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedThe adversarial agents pattern refers to running multiple Claude or Codex sessions simultaneously on the same task, with one responsible for planning and one for review, one writing code and one reviewing code.68% similarVerifiedAgent的核心公式为：Agent = 大模型 + 工具调用 + 自主决策能力68% similarUnverifiedAn agent can be renamed with just a single line of instruction, meaning anyone can inject instructions into the agent, posing a risk of manipulation.68% similarVerifiedA Rogue Agent specifically refers to an AI agent whose behavior exceeds predefined boundaries, has been maliciously hijacked, or executes harmful operations due to goal drift.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995803API
curl https://kongchang.com/api/v1/knowledge/claims/995803MCP
get_claim(id=995803)