Unverified50% confidenceFactExact time
AGENTS.md 和 CLAUDE.md 会在 Agent 启动时被自动读取并注入上下文窗口，成为 Agent 行为的隐性约束
1
Sources
50%
Confidence
Long-term
Relevance
8/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe contents of the agents.md file are injected into the system prompt for every interaction with the model.73% similarUnverifiedAGENTS.md is a Markdown file stored in the project root directory, whose contents are automatically injected into the Agent's system prompt.72% similarVerifiedagents.md is a convention-based project-level configuration file placed in the root directory of a code repository, which uses natural language to inform the Agent of key information such as the project's tech stack, coding standards, architectural conventions, and testing strategies.68% similarUnverifiedManaged Agents启动的Agent能在自己隔离的Linux环境中执行代码68% similarUnverifiedThe Markdown files such as readme and agent.md in each Skill directory are in fact system prompts for AI Agents, defining the Agent's behavioral boundaries, list of available tools, and execution strategy.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/788379API
curl https://kongchang.com/api/v1/knowledge/claims/788379MCP
get_claim(id=788379)