Agent hook
Also written lifecycle hook
A command an agent host runs at fixed points in its loop — before a tool call, after a tool call, when a prompt is submitted, when a session starts or stops — receiving the event as structured data. A hook that runs before a tool call can return a decision, so it is where a policy can allow, ask or deny; the others observe, add context or log. Each host defines its own events and configuration: Claude Code, Codex, Gemini CLI and Cursor all have hooks, under different names.
How MoorAI handles it: MoorAI enforces through the PreToolUse hook in Claude Code and pre-tool hooks in Codex CLI, GitHub Copilot CLI, Gemini CLI and Cursor; its coverage heartbeat reports a hook that was disabled or removed.
See also PreToolUse hook · agent host · Inference hooks
Sources
Related terms
-
PreToolUse hook
Agents & architecture
A callback the agent host invokes after the model has requested a tool call but before the call executes, handing over the tool name and arguments and…
-
Agent host
Agents & architecture
The program that runs the agent loop — the CLI, IDE extension or desktop app that assembles the context, sends it to the model, receives the tool calls…
-
Inference hooks
Agents & architecture
A Claude Enterprise feature, in beta, that sends each governed request to the organization's own AI security server before inference runs and waits for an…
Agents & architecture
Where the attacks above actually land. The vocabulary here is worth precision, because the difference between "the model decided" and "the tool ran" is the difference between a risk and an incident.