CCAR-F Claude Code Configuration and Workflows Practice Question
An engineer repeatedly types the same multi-step instruction: run the unit tests, then fix any failing assertions, then re-run the suite until it passes. They want to invoke this reliably with a short, memorable name in Claude Code. What should they create?
⚠ Common exam trap
The trap here is conflating mechanisms that influence or automate behavior with the one designed for user-invoked, named prompts.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A custom slash command defined as a Markdown file containing the instruction
Custom slash commands exist to capture frequently repeated prompts behind a memorable name. A Markdown command file stores the exact instruction text, and invoking the command by its filename replays that workflow consistently. This is lighter and more predictable than hooks or memory files, and far simpler than standing up an MCP server for a prompt the engineer already writes by hand.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A hook configured in settings.json that fires before every tool call
Why it's wrong here
Hooks run shell commands automatically at lifecycle events such as before or after tool use; they are not user-invoked named workflows. Wiring this repeated instruction into a hook would execute unexpectedly on unrelated events and gives the engineer no short name to call on demand, so it does not match the stated need.
- ✓
A custom slash command defined as a Markdown file containing the instruction
Why this is correct
Custom slash commands are Markdown files whose body becomes the prompt, and they are invoked by name with a leading slash. Saving the test-fix-rerun instruction as a command file gives the engineer a short, memorable trigger that reliably replays the same workflow, and the file can live in a user or project command directory depending on who should share it.
- ✗
An MCP server that exposes the testing workflow as a tool
Why it's wrong here
Building an MCP server is a heavyweight integration approach for exposing external capabilities as tools; it is overkill for replaying a canned prompt. It also requires ongoing process management and configuration rather than the simple file-based, name-invoked mechanism the engineer needs for a repeatedly typed instruction.
- ✗
A new entry in the CLAUDE.md memory file describing the testing preference
Why it's wrong here
CLAUDE.md provides persistent context the model considers, but it is not an invocable action. Content there influences behavior generally rather than executing a specific multi-step routine on demand, so the engineer would still have to type the full instruction and could not trigger it by a short name.
About these practice questions
Courseiva writes every CCAR-F question from scratch — 271 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Anthropic exam blueprint
This CCAR-F practice question is part of Courseiva's free Anthropic certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the CCAR-F exam.