hooks_pre-task · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hooks_pre-task does on Claude Flow

AI agents invoke hooks_pre-task 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 IT NEEDS A POLICY

Why hooks_pre-task needs a policy

This tool executes code/commands via hooks and task routing logic rather than simply reading or writing data. While it may also record metadata (Write), the primary function is triggering task execution workflows in an agent orchestration context. Execution of Bash hooks and model routing constitutes Execute category.

From the tool's definition Tool description mentions 'Record task start' and 'intelligent model routing', indicating it triggers task execution workflows. The reference to 'native Bash hooks' and incomplete phrase 'via Claude Code' suggests the tool executes external commands or code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hooks_pre-task Rate-limited

hooks_pre-task 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hooks_pre-task": {
      "limits": [
        {
          "counter": "hooks_pre-task_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about hooks_pre-task

What does the hooks_pre-task tool do? +

Record task start and get agent suggestions with intelligent model routing (ADR-026) 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.

How do I enforce a policy on hooks_pre-task? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_pre-task: 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.

What risk level is hooks_pre-task? +

hooks_pre-task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit hooks_pre-task? +

Yes. Add a rate_limit block to the hooks_pre-task 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.

How do I block hooks_pre-task completely? +

Set action: deny in the PolicyLayer policy for hooks_pre-task. 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.

What MCP server provides hooks_pre-task? +

hooks_pre-task 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.