Unverified50% confidenceFactExact time
In previous versions, when prompt-type and agent-type hooks were written as natural language instructions, instructions that were supposed to act as blockers instead allowed operations that should have been blocked.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
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.71% similarUnverifiedv2.1.294 optimizes the decision logic of prompt hooks on Stop and SubagentStop events, making Claude less likely to stop a task prematurely.70% similarUnverifiedv2.1.294 fixes the misclassification behavior of instruction-based hooks, enabling them to correctly block according to their literal intent.68% similarUnverifiedClaude 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）68% similarUnverifiedSlash commands typically wait until the current round of tool calls has finished before being processed in order, rather than interrupting ongoing operations.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987089API
curl https://kongchang.com/api/v1/knowledge/claims/987089MCP
get_claim(id=987089)