Q20 of 60 — CCA Practice Exam

Multi-Agent Research System

Your multi-agent research system uses Claude Code with PreToolUse hooks to enforce source-quality rules — blocking subagents from reading low-credibility domains. After deploying, your team reports that one of the three research subagents consistently ignores these restrictions and fetches from blocked sources. You open the session logs and confirm the PreToolUse hook is firing correctly for the other two subagents. Examining the non-compliant subagent's configuration, you find it is defined as a Claude Code subagent file and its matcher field in settings.json reads ["WebFetch", "Bash"]. What is the most likely cause of the hook never firing for that subagent?

A. The subagent is not inheriting the project-level settings.json because subagents don't always load project memory automatically; the rules must be embedded directly in the subagent file body.

B. The matcher field is a JSON array instead of a single string, causing the hook definition to fail schema validation and be silently dropped — so it never fires regardless of which tool is called.

C. The hook events are evaluated at session start, so changes made to settings.json after the subagent was launched are not reflected until the session is restarted.

D. The PreToolUse hook fires for the orchestrator agent only; subagents require a separate SubagentPreToolUse hook event to intercept tool calls at that level.