CCAR-F scenarios › Code Generation with Claude Code · Question 11 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
A new engineer joins and finds that Claude Code ignores the team's error-handling and logging conventions in their sessions, while it follows them reliably for the tech lead. The tech lead says those conventions were added "to my CLAUDE.md" months ago. What is the most likely cause and fix?
Show answer and explanation
Answer: C — The conventions live in the tech lead's user-level ~/.claude/CLAUDE.md, which isn't shared; move them into the project-level CLAUDE.md committed to the repository.
User-level ~/.claude/CLAUDE.md applies only to that user and isn't shared through version control. Conventions the whole team needs belong in project-level configuration (root CLAUDE.md or .claude/CLAUDE.md), and /memory can confirm which files are loaded (task 3.1). A version mismatch (a) doesn't explain behavior that differs by person. Condensing the file (b) still leaves it on one machine. CLAUDE.md is loaded automatically, not on request, so a paste-in command (d) is a workaround for a misunderstanding.
More from this scenario
- Your monorepo has a shared standards folder with files for API design, PCI handling…
- 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…