Unverified85% confidenceFactTime unknown
Claude Code的Hooks机制包括停止钩子（会话结束时自动提议更新CLAUDE.md）和启动钩子（自动加载最新上下文信息）
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Stop Hook can intercept Claude's termination and inject a prompt as a new instruction to continue execution, which is the key to making the entire automated review system work.83% similarUnverifiedClaude Code's Hooks system includes a Stop Hook and a Start Hook, where the Stop Hook triggers a self-reflection process after the AI completes a task.79% similarUnverifiedClaude Code supports lifecycle hooks, which trigger corresponding hook events at nodes such as tool calls, task completion, and session end.77% similarUnverifiedClaude Code's Hooks mechanism supports trigger scenarios including PRE-TOOL USE, POST-TOOL USE, SESSION START, and SESSION END77% similarUnverifiedClaude Code's Hooks execution is synchronously blocking, meaning the AI must wait for the Hook script to finish executing before proceeding to the next step.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17447API
curl https://kongchang.com/api/v1/knowledge/claims/17447MCP
get_claim(id=17447)