Be able to launch Claude Code in the correct directory, supply context for multi-file work, read error output to find the cause, and place project guidelines where the whole repository inherits them. The key is knowing which configuration level applies to a team versus an individual.
Start practicing
Claude Code Configuration and Workflows — choose a session length
Free · No account required
Domain overview
This domain covers setting up and operating Claude Code in real repositories: starting sessions, giving the model the right context, and steering behavior with project-level configuration. Questions are scenario-based, presenting terminal output, developer goals, or team-wide policy needs, then asking which command, file, or workflow resolves them correctly.
Exam objectives
Starting a Claude Code session in a directory and letting it index local files
Configuring project-level guidelines and system prompts for an enterprise repository
Choosing efficient workflows for large multi-file refactors with sufficient context
Diagnosing Claude Code failures from terminal error logs and workflow symptoms
Assuming Claude Code automatically reads every file; context must be supplied deliberately via the working directory, references, or project configuration.
Putting team-wide guidelines in personal or global settings instead of the repository's project-level configuration that all contributors inherit.
Treating a refactor as many separate manual file reads rather than one scoped session with the relevant files and instructions provided up front.
Click any question to see the full explanation and answer options, or start a focused practice session above.
During an interactive session, Claude Code identifies a bug and proposes a fix that requires executing a shell command to install a new dependency. How does the default permission model handle this request?
2Which command is used to start a new Claude Code session in the current directory and begin indexing the local files?
3Refer to the exhibit. A developer sees this error log in the terminal output. What is the most likely cause of this failure in the Claude Code workflow?
4How does Claude Code handle large repositories that exceed the standard context window size during initial indexing?
5What is the primary purpose of the 'compact' workflow in Claude Code configuration?
6A developer wants to use Claude Code to perform a large refactor across multiple files. What is the most efficient workflow to ensure the model has the necessary context without manual file-by-file reading?
7A developer needs to integrate a third-party tool that provides real-time logs to Claude Code. Which configuration section in the .clauderc file is responsible for defining these external integrations?
8In a scenario where a project-specific .clauderc file and a global ~/.clauderc file both define a 'model' setting, which one takes precedence when Claude Code is launched from that project directory?
9Refer to the exhibit. A developer is experiencing slow response times during complex refactoring tasks. Based on the provided configuration, what is the most likely cause of performance issues?
10A team wants to optimize their Claude Code workflow for a large monorepo. Which TWO of the following actions improve performance and context relevance?
11What is the primary purpose of the 'claude_config.json' file in a local project?
12When troubleshooting an issue where Claude Code is failing to suggest relevant file modifications, which workflow step should be performed first?
13Which mechanism does Claude Code use to maintain session state across multiple prompts during a single refactoring task?
14When Claude Code suggests a series of file edits, what is the best strategy to ensure the integrity of the project?
15How should a team handle multiple developers using Claude Code on the same shared repository?
16Which of the following describes the correct relationship between Claude Code's indexing process and the file system?
17An engineering team wants to customize Claude Code behavior across their enterprise repository by enforcing specific project-level guidelines and system prompts. Where should the lead architect place these configuration directives so that Claude Code automatically detects and applies them upon initialization in the workspace root?
18A developer is using Claude Code to refactor a large TypeScript repository. They notice that Claude Code is attempting to read and analyze thousands of generated log files in the /dist folder, slowing down performance. Which configuration change should the developer make to optimize this workflow?
19Which TWO of the following practices should be implemented to ensure Claude Code operates securely within a production-adjacent environment?
20A developer wants Claude Code to automatically run the project's linter after every file edit, but only for files inside the `src/` directory. Where should this be configured so the behavior applies to all contributors of the repository?
21A developer working in a monorepo wants Claude Code to follow the team's TypeScript conventions only when editing files under the `packages/api` directory, while letting other directories use different conventions. What is the most appropriate way to configure this in Claude Code?
22A new engineer on a team wants to see every slash command currently available in their Claude Code session, including custom commands the team has added, before starting a large refactor. Which action should they take?
23An 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?
24A platform team wants Claude Code to automatically run the project's formatter after every file edit made by the assistant, so that generated code always matches the repository style without manual intervention. Which configuration should the team use?
25A consultant is preparing a Claude Code setup for a client whose repository must never send secrets to the model. The consultant wants to block reads of `.env` files and any file under a `secrets/` directory at the tool level. Which configuration achieves this?
26An architect is onboarding a large team to Claude Code and wants to standardize how project-level configuration is shared through version control so that every developer gets the same behavior. Which two practices should the architect adopt? (Choose two.)
27A platform team maintains a shared monorepo. A developer runs Claude Code and wants the tool to automatically treat every file under `/infra/terraform/` as read-only for all engineers, without relying on each person to remember a flag. Where should this restriction be declared so it applies to everyone who opens the repo?
28A developer is working on a legacy monorepo where the Claude Code CLI's auto-generated commit messages keep mixing unrelated changes from multiple microservices. To improve this, the developer wants Claude Code to read a project-specific file that describes the commit message format and scope conventions. Which file should the developer create at the repository root to provide this persistent, team-shared guidance?
29An architect is onboarding a legacy service and wants Claude Code to build context quickly. The repository has 40,000 files, most of them generated build artifacts and vendored dependencies, and the team wants exploration to stay focused on first-party source. Which approach best keeps Claude Code's automatic context gathering efficient here?
30A platform team wants Claude Code to be allowed to run only a specific set of safe Bash commands (for example, `npm test` and `git status`) without prompting, while still blocking arbitrary shell commands. They want this policy applied automatically to every developer who clones the repository. Where should they define this allowlist so it is version-controlled and enforced for the whole team?
31A developer wants Claude Code to always run the project's formatter after it edits a file, and wants this behavior shared with the whole team through version control. Which configuration mechanism is intended for this kind of automatic, tool-triggered action?
32A developer frequently runs the same multi-step task in Claude Code: lint the changed files, run the unit tests, and then draft a commit message. They want to invoke this entire sequence with a single reusable command rather than retyping the instructions each time. Which Claude Code feature should they configure?
33You are a Claude Code user working on a Python project. You want to define a custom slash command named /test that runs your project's test suite. Where should you place the command file so that it is available only within this project?
34A security-conscious architect is standardizing how Claude Code is configured across a large engineering organization. Which TWO practices best reduce the risk introduced by project-level configuration that arrives with cloned repositories? (Choose two.)
35During a long refactoring session, a developer realizes Claude Code has been operating with an outdated understanding of a utility module because the file was changed on disk by a teammate's branch merge. The developer wants Claude to re-read the current contents of that file before continuing. Which action accomplishes this most directly?
36A developer wants to ensure that Claude Code automatically uses a specific set of custom instructions for every session in a particular repository, without requiring manual invocation. They want these instructions to be version-controlled and applied to all team members. Which approach should they take?
37A new engineer joins a team and clones the project repository. They run Claude Code and find it already follows the team's conventions for commit messages and test layout without any personal setup. Which explanation accounts for this?
38An architect is standardizing Claude Code usage across a large engineering organization. They want to ensure that every developer's sessions automatically inherit a curated set of project conventions and that destructive shell commands are blocked unless explicitly approved. Which TWO configurations should the architect implement? (Choose two.)
39A team is configuring Claude Code for a new project. They want to enforce specific tool permissions to prevent Claude Code from executing potentially dangerous shell commands without approval. Which two configuration approaches should they use? (Choose two.)
40A developer wants a single Claude Code slash command available only to their own user account on a shared Linux workstation, not to other engineers who log into the same machine. Where should the command's Markdown file be stored?
41A developer new to Claude Code wants to quickly see a list of all available slash commands in their current session. Which command should they use?
42A platform team maintains a repository where a committed .claude/settings.json grants broad Bash permissions, but an engineer needs a stricter personal policy that still allows the shared project settings for everything else. Which approach correctly applies the engineer's narrower permission policy?
43While working in a repository, an architect wants Claude Code to explain the purpose of a specific function in a large source file without altering any code or generating new files. Which mode should be used for this task?
44An 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?
Be able to launch Claude Code in the correct directory, supply context for multi-file work, read error output to find the cause, and place project guidelines where the whole repository inherits them. The key is knowing which configuration level applies to a team versus an individual.
The Courseiva CCAR-F question bank contains 44 questions in the Claude Code Configuration and Workflows domain. Click any question to see the full explanation and answer breakdown.
Start with a 10-question focused session to identify your baseline accuracy in this domain. Read every explanation — even for questions you answer correctly — to understand the reasoning. Once you score consistently above 80%, move to a 20–30 question session to confirm depth before moving to the next domain.
Yes — the session launcher on this page draws questions exclusively from the Claude Code Configuration and Workflows domain. Choose 10, 20, 30, or 50 questions for a focused session, or click individual questions to review them one by one.
Save your results, see per-domain analytics, and get readiness scores — free, for every certification.
Sign Up FreeFree forever · Every certification included