Reset intelligence learning state Use when native Bash hooks (via Claude Code\
AI agents call hooks_intelligence-reset to permanently remove resources in Claude Flow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting a learning state discards all previously accumulated intelligence/training data for the hooks system. This is irreversible (you cannot un-reset learned state), making it Destructive. The blast radius is high because it could wipe out significant learned behavior across an enterprise AI orchestration system with 87 tools and hive-mind swarms.
From the tool's definition 'Reset intelligence learning state' — resetting learning state is an irreversible operation that destroys accumulated model/agent intelligence data
Attacks that exploit this kind of access
Reset intelligence learning state Use when native Bash hooks (via Claude Code\. It is categorised as a Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_intelligence-reset: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Flow. Nothing to install.
hooks_intelligence-reset is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the hooks_intelligence-reset rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hooks_intelligence-reset. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hooks_intelligence-reset is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.