CoursesFree Quizzes
AnthropicClaude Code

Claude Code & Settings — CCDV-F Practice Question

A representative Claude Certified Developer - Foundations (CCDV-F) exam question on Claude Code & Settings. Work through it below, then read why each option is right or wrong.

This question is part of the free Claude Certified Developer - Foundations practice test.

Short answer

The correct answer is A. Use the 'permissions' block in a .claude/settings.json file to set specific tool allow/deny rules, restricting bulk file-write tools to require approval while permitting read-only tools to run automatically..

Claude Code's .claude/settings.json supports a 'permissions' block where operators can explicitly allow or deny individual tools and require human approval for sensitive actions. This is the authoritative mechanism for controlling tool invocation behavior at the repository level. A CLAUDE.md description alone provides context but does not enforce tool restrictions—Claude may still invoke disallowed tools. Switching models via ANTHROPIC_MODEL addresses cost, not permission enforcement. A pre-commit hook operates on git commits, not on Claude Code tool execution, and cannot selectively restrict specific tools mid-session.

The Question

A media archive company stores millions of video assets and uses Claude Code to automate metadata tagging. Traffic spikes unpredictably when major events occur, causing Claude Code sessions to attempt bulk file operations that overwhelm the archive's storage API. The team wants to use repository-level configuration to constrain which tools Claude Code can invoke automatically versus which ones require explicit human approval. Which Claude Code settings mechanism best addresses this integration tradeoff?

AUse the 'permissions' block in a .claude/settings.json file to set specific tool allow/deny rules, restricting bulk file-write tools to require approval while permitting read-only tools to run automatically.Correct
BSet the ANTHROPIC_MODEL environment variable to a smaller model during high-traffic periods so fewer tokens are consumed per session, reducing API pressure.
CCreate a pre-commit hook that cancels any Claude Code session exceeding a fixed token count, preventing runaway bulk operations at the repository level.
DAdd a CLAUDE.md file at the repository root that describes the storage API limits in plain text, relying on Claude to infer safe behavior from the description alone.

Why A is correct

Claude Code's .claude/settings.json supports a 'permissions' block where operators can explicitly allow or deny individual tools and require human approval for sensitive actions. This is the authoritative mechanism for controlling tool invocation behavior at the repository level. A CLAUDE.md description alone provides context but does not enforce tool restrictions—Claude may still invoke disallowed tools. Switching models via ANTHROPIC_MODEL addresses cost, not permission enforcement. A pre-commit hook operates on git commits, not on Claude Code tool execution, and cannot selectively restrict specific tools mid-session.

Why the other options are wrong

Option B: Set the ANTHROPIC_MODEL environment variable to a smaller model during high-traffic periods so fewer tokens are consumed per session, reducing API pressure.

Option B does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (A) is the only one that fully meets every constraint stated in the question.

Option C: Create a pre-commit hook that cancels any Claude Code session exceeding a fixed token count, preventing runaway bulk operations at the repository level.

Option C does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (A) is the only one that fully meets every constraint stated in the question.

Option D: Add a CLAUDE.md file at the repository root that describes the storage API limits in plain text, relying on Claude to infer safe behavior from the description alone.

Option D does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (A) is the only one that fully meets every constraint stated in the question.

Key idea: Claude Code & Settings

Claude Code's .claude/settings.json supports a 'permissions' block where operators can explicitly allow or deny individual tools and require human approval for sensitive actions. This is the authoritative mechanism for controlling tool invocation behavior at the repository level. A CLAUDE.md description alone provides context but does not enforce tool restrictions—Claude may still invoke disallowed tools. Switching models via ANTHROPIC_MODEL addresses cost, not permission enforcement. A pre-commit hook operates on git commits, not on Claude Code tool execution, and cannot selectively restrict specific tools mid-session. On the CCDV-F exam, questions in the "Claude Code" domain test whether you can map a scenario's constraints to the right choice. Read the requirement carefully, eliminate options that violate any single constraint, and pick the one that satisfies all of them with the least operational overhead.

Ready to see how you'd score?

Take the free practice quiz and find out which Claude Certified Developer - Foundations domains you need to focus on. No signup required.

Take the free quizSee all 20+ practice questions

Practice 5 similar questions

Same cert, same or adjacent domain. Use these after reviewing the explanation.

1Agents & Workflows — CCDV-F Practice QuestionAgents and Workflows2Messages API & Conversation — CCDV-F Practice QuestionApplications and Integration3Claude Code & Instructions — CCDV-F Practice QuestionClaude Code4Evals & Regression — CCDV-F Practice QuestionEval, Testing, and Debugging5Model Selection & Routing — CCDV-F Practice QuestionModel Selection and Optimization

Related Claude Certified Developer - Foundations Practice Questions

Agents & Workflows — CCDV-F Practice Question→Messages API & Conversation — CCDV-F Practice Question→Claude Code & Instructions — CCDV-F Practice Question→

Official sources used

Verify program and exam details at the source before scheduling.

AnthropicClaude Code: SettingsAnthropic AcademyClaude Certified Developer Foundations Certification