CCARF Practice Question

Paper 3 · Question 12

D3 Claude Code Configuration & Workflows · Paper 3

[Scenario 2: Code Generation with Claude Code] Your team uses Claude Code for code generation, refactoring, debugging, and documentation, integrated into daily development with custom slash commands and CLAUDE.md configuration — and you must judge when plan mode beats direct execution. Your /analyze-architecture skill produces thousands of lines of exploration output that pollute the main conversation, crowding out the task you actually wanted help with. Which SKILL.md frontmatter option fixes this?

• A.argument-hint, so the skill asks what to analyze
• B.context: fork, which runs the skill in an isolated sub-agent context and returns results without flooding the main conversation
• C.allowed-tools, restricting the skill to read-only operations
• D.paths, restricting the skill to architecture files

Show answer & explanations

Correct answer: B

A: governs parameter prompting

B: context: fork exists for exactly this: verbose or exploratory skills run in their own isolated context, and the main session receives the distilled result rather than the full exploration transcript.

C: governs which tools the skill may use — neither controls where output accumulates

D: is rules-file syntax, not skill frontmatter for isolation

Related Claude Code Configuration & Workflows questions

More: Paper 3 · All practice questions