Practice Free CCA-F Exam Online Questions
When authoring a complex skill, relying on a massive 2000-line SKILL. md file wastes context window tokens.
Which of the following describe the recommended "progressive disclosure" architectural pattern? Choose 2 correct answers.
- A . Keep the SKILL .md file under 500 lines and link to supporting reference files that Claude reads only when needed.
- B . Store executable validation code in a scripts/directory and instruct Claude to run them rather than read their contents.
- C . Use the fork_session command explicitly on line 1 of the markdown to split the file structure.
- D . Configure an automatic /compact command to execute every 10 turns within the skill definition.
A engineering team wants to share formatting rules, testing guidelines, and preferred libraries across their entire repository.
Where is the correct location to configure these team-wide standards in Claude Code?
- A . In the user-level configuration file located at ~/. claude/CLAUDE. md.
- B . In the project-level configuration file located at. claude/CLAUDE. md or the project root.
- C . In a directory-level configuration file located at tests/CLAlJDE .md.
- D . In the global .mcp.json file.
What configuration is strictly required for a coordinator agent to be able to spawn subagents?
- A . The tool_choice parameter must be set to ‘auto’.
- B . The coordinator’s allowedTools array must explicitly include the Task tool.
- C . The agent must be executed in plan mode rather than direct execution.
- D . A PreToolUse hook must be registered to manage process limits.
In a coordinator-subagent research system, a web search subagent times out while attempting to retrieve information on a complex topic.
How should this failure be propagated back to the coordinator agent?
- A . The subagent should catch the timeout and return an empty JSON array L] marked as successful so the workflow continues smoothly.
- B . Propagate the timeout exception directly to a top-level handler to immediately terminate the entire research workflow.
- C . Implement automatic retry logic indefinitely within the subagent, returning a generic search unavailable status if it ultimately fails.
- D . Return structured error context to the coordinator, including the failure type, the attempted query, any partial results, and potential alternative approaches.
You are designing an MCP interface for a backend system.
When should you choose to implement an MCP Resource instead of an MCP Tool?
- A . When you need the model to execute side-effects, such as updating a database record.
- B . When you want to expose a static content catalog or documentation that can be fetched to provide context without requiring exploratory tool calls.
- C . When you need to provide pre-built conversation templates.
- D . When you need to execute bash commands on the local machine.
You must enforce a strict business rule that the agent escalates any refund request exceeding $500.
What is the most deterministic method to implement this?
- A . Add a capitalized warning in the system prompt explicitly forbidding high-value refunds.
- B . Provide 5 negative few-shot examples showing the agent refusing high-value refunds.
- C . Use an Agent SDK hook (e.g., PreToolUse or PostToolUse) to programmatically intercept and block the action.
- D . Configure tool_choice to ‘auto’ so the model can dynamically assess the financial risk.
To guarantee that a specific data extraction tool is invoked by Claude during a workflow without the agent attempting conversational workarounds, which configuration must be applied?
- A . tool choice: "auto"
- B . tool_choice: "any"
- C . tool_choice: {"type": "tool", "name": "SPECIFIC_TOOL NAME"}
- D . allowedTools: ["SPECIFIC_TOOL NAME"}
You are creating a reusable skill for an automated code review process. You want the skill to analyze the codebase extensively without polluting the main conversation’s context window with its exploratory output.
Which frontmatter configuration is required?
- A . isolation: true
- B . context: fork
- C . sandbox: enabled
- D . execution_mode: background
Where should a development team configure a shared Jira MCP server to ensure credentials are NOT leaked in version control?
- A . In the user-level 4. claude. json file, requiring each team member to manually script the configuration.
- B . In the project-level .mcp.json file, using environment variable expansion syntax like
- C . Inside a dedicated secrets. json file that is committed to the repository.
- D . As inline comments within the CLAUDE. md file.
To mitigate the ‘lost in the middle’ effect when passing a large set of aggregated documents to Claude, where should you place the most critical instructions and key findings summaries?
- A . Evenly distributed throughout the middle of the document chunks.
- B . At the beginning and end of the aggregated input.
- C . Inside a hidden HTML comment block <!– –>.
- D . In a separate PostToolUse hook payload.