performance_optimize

What performance_optimize does on Claude Flow

AI agents invoke performance_optimize 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 performance_optimize is rated High

The tool applies optimizations (not merely reporting metrics) which implies triggering external operations whose effects depend on arguments. The mention of 'shell timing' suggests potential shell command execution or system-level intervention. While the description is truncated and uninformative, the action verb 'Apply' paired with 'performance optimizations' on an orchestration server indicates Execute-class risk.

From the tool's definition Tool name 'performance_optimize' combined with description fragment 'Apply performance optimizations Use when native shell timing' indicates execution of optimization operations, likely on agent infrastructure or system-level performance tuning.

The rule that runs performance_optimize 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 performance_optimize, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "performance_optimize": {
      "limits": [
        {
          "counter": "performance_optimize_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about performance_optimize