---
title: "Agent SDK hooks — CCAR-F 1.5 practice questions"
description: "8 CCAR-F practice questions on objective 1.5: Agent SDK Hooks. Part of domain 1, Agentic Architecture and Orchestration."
url: "https://claudearchitectguide.com/ccar-f/drill/obj/1-5"
image: "https://claudearchitectguide.com/og.png"
---

CCAR-F objective 1.5 · Domain 1 · 27% of the exam

# Agent SDK Hooks

Thirty-one hook events exist and perhaps eight are settled enough to examine, so the mechanics matter more than the roster. Exit status 2 is the only code that blocks on its own; every other non-zero status is a non-blocking error and the action goes ahead. PostToolUse cannot block anything, because the tool has already run, and anybody expecting it to veto a write has the lifecycle wrong. Tool events answer with permissionDecision, which takes three values and not two: allow, deny, escalate. Lifecycle events such as Stop use a different key entirely.

8 questions · answers and explanations shown as you go · free, no sign-up

## The rest of domain 1: Agentic Architecture and Orchestration

This domain is 27% of a scored form, about 17 of the 65 questions, spread across 7 objectives. [Drill the whole domain](https://claudearchitectguide.com/ccar-f/drill/1) or pick another objective below.

- [1.1 Agentic Loops (8)](https://claudearchitectguide.com/ccar-f/drill/obj/1-1)
- [1.2 Multi-Agent Orchestration (8)](https://claudearchitectguide.com/ccar-f/drill/obj/1-2)
- [1.3 Subagent Invocation and Context Passing (8)](https://claudearchitectguide.com/ccar-f/drill/obj/1-3)
- [1.4 Workflow Enforcement and Handoff (8)](https://claudearchitectguide.com/ccar-f/drill/obj/1-4)
- [1.6 Task Decomposition Strategies (7)](https://claudearchitectguide.com/ccar-f/drill/obj/1-6)
- [1.7 Session State and Resumption (7)](https://claudearchitectguide.com/ccar-f/drill/obj/1-7)

One objective is a narrow slice. A full-length timed mock is what tells you whether the whole thing holds together.

[Sit a timed mock →](https://claudearchitectguide.com/ccar-f/exam)
