CCAR-F Claude Code Configuration and Workflows Practice Question
An architect is onboarding a new developer to a repository that uses Claude Code. The developer wants to understand how the tool determines which project-specific instructions to load automatically at the start of a session. The repository already contains a CLAUDE.md file at the root. What is the correct behavior of Claude Code regarding this file?
⚠ Common exam trap
The trap here is assuming that project memory requires an explicit import command or a settings.json reference, when Claude Code actually discovers and loads CLAUDE.md by convention at session start.
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
✓
Claude Code automatically reads the CLAUDE.md file from the project root and includes its contents as context for the session.
The CLAUDE.md file at the project root is automatically ingested as context when Claude Code starts in that directory, which is how teams distribute conventions and architectural notes. No manual import or settings.json entry is required, and the file is not merely a write-only scratchpad. This automatic loading is what makes project memory reliable across sessions.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Claude Code only reads CLAUDE.md if it is referenced inside a .claude/settings.json configuration file.
Why it's wrong here
The settings.json file manages permissions, hooks, and environment variables, not the loading of CLAUDE.md. Project memory is discovered by convention based on file name and location, not by an entry in settings.json. Adding a reference there would have no effect on whether the memory file is read.
- ✗
Claude Code ignores CLAUDE.md unless the developer explicitly runs a command to import it at the beginning of each session.
Why it's wrong here
CLAUDE.md is loaded automatically, not on demand. Requiring a manual import command would defeat the purpose of persistent project memory and would make onboarding inconsistent. The file is designed to be picked up as soon as Claude Code initializes in the project directory, so no explicit import step is needed.
- ✗
Claude Code treats CLAUDE.md as a scratchpad that is only written to and never read as context during a session.
Why it's wrong here
CLAUDE.md is bidirectional in practice: it is read as context and can be updated with the # shortcut to persist new instructions. Describing it as write-only misrepresents its primary role. The model relies on its contents for guidance, so a scratchpad-only interpretation would eliminate the file's main architectural benefit.
- ✓
Claude Code automatically reads the CLAUDE.md file from the project root and includes its contents as context for the session.
Why this is correct
CLAUDE.md is the designated project memory file. When Claude Code starts in a directory containing this file, it automatically loads the content into the context window, giving the model project-specific guidance without any manual action. This is the intended mechanism for sharing architecture notes, coding conventions, and workflow instructions across a team.
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.