CCAR-F scenarios › Code Generation with Claude Code · Question 12 of 60
Scenario 2 · Code Generation with Claude Code
Your engineering team relies on Claude Code to generate, refactor, debug, and document code. You're responsible for fitting it into the team's workflow: custom slash commands and skills, a sensible CLAUDE.md setup, and knowing when a task calls for plan mode and when direct execution is enough.
Claude Code Configuration & Workflows
Your monorepo has a shared standards folder with files for API design, PCI handling, accessibility, and data retention. The root CLAUDE.md has grown past 1,500 lines by copying all of them in, and package maintainers say most of it is irrelevant to their package. The payments package needs only the API and PCI standards. What is the most maintainable approach?
Show answer and explanation
Answer: A — In each package's CLAUDE.md, use @import to reference only the standards files that package needs, for example the API and PCI files for payments, chosen by its maintainers.
@import keeps CLAUDE.md modular: each package pulls in only the standards files relevant to it, chosen by maintainers who know the domain, while one source of truth stays in the shared folder (task 3.1). One giant file with headers (b) still loads everything and relies on inference. Skills (c) are on-demand, so standards that should always apply depend on developers remembering to invoke them. Copying text by hand (d) creates duplicates that drift apart.
More from this scenario
- The root CLAUDE.md has a long section on database migration conventions. Migration files…
- Your team's /map-dependencies skill reads dozens of files and produces several thousand…
- Two hours into exploring an unfamiliar payments codebase, Claude Code's answers start to…
- Your team is deciding which upcoming tasks should start in plan mode and which can go…
- You ask Claude Code to convert legacy log lines into a new structured format. Despite…