hooks_intelligence_learn
Force immediate SONA learning cycle with EWC++ consolidation Use when native Bash hooks (via Claude Code\
This record as markdown: /tools/io-github-ruvnet-claude-flow/hooks-intelligence-learn.md
What hooks_intelligence_learn does on Claude Flow
AI agents invoke hooks_intelligence_learn to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why hooks_intelligence_learn is rated High
This tool forcibly triggers an active learning/consolidation cycle in what appears to be a neural network or AI system (SONA with EWC++ consolidation), and invokes Bash hooks via Claude Code. Forcing a learning cycle modifies internal model state and executes external hooks, placing it in Execute. The blast radius is high because misuse could corrupt the AI agent's learned state or trigger unintended Bash operations.
From the tool's definition 'Force immediate SONA learning cycle with EWC++ consolidation' and 'Use when native Bash hooks (via Claude Code'
Attacks that exploit this kind of access
The rule that runs hooks_intelligence_learn safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hooks_intelligence_learn, this is the rule to start with:
hooks_intelligence_learn stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every hooks_intelligence_learn call is checked against it from then on.
Questions about hooks_intelligence_learn
Force immediate SONA learning cycle with EWC++ consolidation Use when native Bash hooks (via Claude Code\. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_intelligence_learn: 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_learn is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hooks_intelligence_learn 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_learn. 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_learn 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.
More on Claude Flow, and thousands of servers like it.
Across the catalogue