Be able to supervise an agentic loop: give a clear goal, let Claude Code plan, run tools, and self-correct on failures, and approve risky actions. The key is knowing when to intervene with context versus when to let the agent iterate on its own.
Start practicing
Claude Code — choose a session length
Free · No account required
Domain overview
This domain covers Claude Code as an agentic terminal tool: how it plans multi-step work, runs tools, reacts to failures, and keeps a human in the loop. Questions are scenario-based, asking you to pick the right developer action, judge safe versus unsafe operations, and describe how execution flow and error recovery actually work.
Exam objectives
How Claude Code plans and sequences multi-step tasks, tracking progress toward completion across tool calls.
Using CLAUDE.md project memory and /init to give the agent persistent context and conventions.
Guiding failure recovery: reading test output, forming a hypothesis, and letting the agent edit and re-run.
Safe standard actions like reading files, running tests, and searching, versus destructive or network operations.
Assuming the agent needs step-by-step manual instructions instead of letting it plan and iterate on its own.
Pasting raw error text without context rather than pointing the agent at the failing test and letting it investigate.
Treating every file write or command as safe; destructive actions like force-push or mass deletion still need approval.
Click any question to see the full explanation and answer options, or start a focused practice session above.
Which TWO of the following capabilities are native to Claude Code when operating in a repository?
2What is the primary purpose of the 'claude' command-line interface tool?
3When Claude Code executes a shell command that requires user intervention (such as an interactive prompt), how does the agent typically handle this situation?
4Which THREE of these actions are considered safe and standard for Claude Code to perform during an interactive session?
5How does Claude Code maintain context over a long-running conversation in the terminal?
6A developer wants to integrate Claude Code into a CI/CD pipeline. Why is this generally discouraged or difficult to achieve directly?
7When should a developer choose to 'reject' an edit suggested by Claude Code?
8Which of the following is an example of an effective natural language instruction for Claude Code?
9When Claude Code is asked to perform a complex, multi-file task, how does it typically approach the problem?
10What is the role of the user when using Claude Code for a complex refactoring task?
11Refer to the exhibit. Claude Code has encountered a test failure while implementing a feature. How should the developer effectively guide the agent to resolve this error using the agent's internal capabilities?
12When Claude Code is asked to perform a complex task that might take a long time, how does the agent manage the execution flow to ensure task completion?
13Refer to the exhibit. You are working with Claude Code and receive this error message during a batch refactor. What is the most appropriate course of action?
14What is the primary purpose of the 'Claude Code' tool in a professional development environment?
15A developer notices that Claude Code is hallucinating about the availability of a specific CLI tool that is not installed in the current environment. What is the most effective way to correct this behavior?
16Refer to the exhibit. How does Claude Code handle this interruption, and what is the expected outcome?
17What role do 'project-aware' features play in Claude Code during a development session?
18Why is it important to use the Claude Code CLI within an initialized Git repository?
19Refer to the exhibit. What is the most effective way to address the agent's modification of build artifacts?
20You are working in a monorepo where the repository root contains a CLAUDE.md with shared coding standards, and the packages/api directory has its own CLAUDE.md with API-specific conventions. During a session started from the repository root, Claude Code begins editing files under packages/api. Which CLAUDE.md content is applied to those edits, and how should you expect the two files to interact?
21A developer is working in a large repository and wants Claude Code to understand the project structure and available tools before making changes. They run `claude` in the project root. Which action best ensures Claude Code has the necessary context for the session?
22A developer is using Claude Code to refactor a function across multiple files. After a few edits, Claude Code proposes a change that would alter the behavior of a critical utility function used elsewhere. The developer wants to ensure the change is safe before applying it. What is the most appropriate action?
23A developer wants Claude Code to remember a project-specific convention: all new database migration files must be placed in the `db/migrations` directory and named with a `YYYYMMDDHHMMSS_` prefix. The developer wants this rule applied automatically in every future Claude Code session for this repository, without having to repeat the instruction each time. What is the most appropriate way to achieve this?
24A developer is working on a large refactoring task with Claude Code. They want to ensure the agent has sufficient context about the project's architecture and coding standards. Which TWO of the following are recommended ways to provide this context? (Choose two.)
25A developer is onboarding to an unfamiliar Python service and wants to use Claude Code to build an accurate mental model of how requests flow through the codebase before making changes. Which TWO actions best leverage Claude Code for this exploration task? (Choose two.)
26A developer wants Claude Code to add input validation to a specific function in `src/api/users.py`. Which instruction is most likely to produce a correct, targeted change?
27A developer is working in a large monorepo and wants Claude Code to automatically run `npm run lint` and `npm run test` after every file edit it makes, without needing to ask each time. Which Claude Code feature should the developer configure to achieve this?
28A developer is using Claude Code to debug a complex issue. After several exchanges, Claude Code suggests a solution that involves modifying a configuration file outside the project directory. The developer is concerned about unintended side effects. What is the most appropriate way to handle this?
29A team wants Claude Code to run a custom script that inspects the repository for license headers before any commit. The script must run automatically each time Claude Code is about to create a commit, and the team wants the same hook to apply to every developer without manual setup. Which mechanism should they use?
30A developer wants Claude Code to understand the team's API conventions, directory layout, and preferred testing framework for a specific service, and wants that guidance loaded automatically at the start of every session in that repository without typing it. What is the most appropriate way to accomplish this?
31A developer wants Claude Code to run a series of shell commands as part of a build task but is concerned about the assistant executing arbitrary or destructive commands. Which TWO practices reduce this risk while still allowing the needed commands to run? (Choose two.)
32A developer repeatedly types the same multi-step instruction to Claude Code: review the current diff, run the unit tests, and summarize any failures. They want to trigger this workflow with a single short command in future sessions. What should they create?
Be able to supervise an agentic loop: give a clear goal, let Claude Code plan, run tools, and self-correct on failures, and approve risky actions. The key is knowing when to intervene with context versus when to let the agent iterate on its own.
The Courseiva CCDV-F question bank contains 32 questions in the Claude Code 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 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