Unverified50% confidenceFactExact time
The Claude Agent SDK's PreToolUse and PostToolUse hooks, combined with matchers such as Write|Edit, can block, modify, or log tool calls.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedClaude Code's Hooks have five lifecycle events: User Prompt Submit, Pre-tool Use, Post-tool Use, Notification, and Stop.69% similarUnverifiedHook event types include PreToolUse, PostToolUse, and Notification; if a PreToolUse script returns exit code 2, the tool call is blocked.64% similarUnverified@ai-sdk/vue encapsulates the tool-calling workflow; developers only need to declare the parameter Schema for a tool, and the SDK automatically handles invocation instructions, result callbacks, and multi-turn conversation state management.62% similarUnverifiedAnthropic has implemented an anti-injection process for the Claude Fable 5.1 API, requiring that when resuming old inference records the original chat history, system prompt, and tool configuration must remain unchanged, otherwise the request is rejected.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007812API
curl https://kongchang.com/api/v1/knowledge/claims/1007812MCP
get_claim(id=1007812)