configuring-claude-codelisted

# Configuring Claude Code ## Overview Best-practice reference for repository-level Claude Code setup: memory files, skills/commands, conditional convention loading, execution modes, and CI. Each reference module states the correct pattern, the named anti-patterns, and ends with an **Audit Checklist** of verifiable conditions. ## When to use - Setting up a repo: CLAUDE.md structure, `.claude/rules/`, skills, slash commands - Debugging: ignored instructions, conventions applied in the wrong directories, oversized memory files - Deciding: plan mode vs direct execution, where a rule belongs, batch vs real-time review in CI Not for prompt content of the tasks themselves (use engineering-prompts-and-output). ## Quick reference | Module | Read when the question is about | |---|---| | `references/3-1-claude-md-hierarchy-scoping-and-modular-organisation.md` | Memory hierarchy, loading/conflict order, `@` imports, modular organisation | | `references/3-2-custom-slash-commands-and-skills.md` | Skills system, scoping levels, frontmatter, skills vs CLAUDE.md | | `references/3-3-path-specific-rules-for-conditional-convention-loading.md` | Glob-based rules vs directory/root CLAUDE.md | | `references/3-4-plan-mode-vs-direct-execution.md` | When to plan, Explore subagent, plan-then-execute hybrid | | `references/3-5-iterative-refinement-techniques.md` | Refinement hierarchy, batch vs sequential feedback, example-based communication | | `references/3-6-ci-cd-integration.md` | Headless `