Claude Code Configuration & Workflows

Key terms and definitions for Domain 3. Each entry includes a concise definition, exam context, and links to the relevant lesson.

Jump:

10 of 10 terms

A

allowedTools

A settings array that specifies which tools Claude Code can use without asking for permission. Supports glob patterns for matching tool names. Tools not in this list require user approval before execution.

Exam Context

Know the glob syntax for matching tool families. Understand that allowedTools is a whitelist, not a blacklist. Combining with deniedTools creates a layered permission model.

C

CI/CD Integration

Running Claude Code in non-interactive mode within continuous integration pipelines. Uses the --print flag for single-shot execution and --dangerously-skip-permissions for automated environments where no human can approve tool use.

Exam Context

Know the flags: --print (non-interactive), --dangerously-skip-permissions (auto-approve all tools). Understand security implications of skipping permissions in CI.

CLAUDE.md

A markdown file that provides persistent context and instructions to Claude Code. Can be placed at project root, user home directory (~/.claude/CLAUDE.md), or in subdirectories. Claude reads these files at session start to understand project conventions.

Exam Context

Know the hierarchy: user-level, project-level, and directory-level CLAUDE.md files. Project-level is most common. Content should include coding standards, project structure, and key conventions.

H

Hook

A shell command that executes at specific lifecycle points in Claude Code. Hooks run before tool calls (PreToolUse), after tool calls (PostToolUse), and on notifications. They enable logging, validation, and custom automation.

Exam Context

Know the three hook types and their timing. PreToolUse hooks can block tool execution by returning a non-zero exit code. PostToolUse hooks can inspect results.

P

Permission

A configuration that controls which tools Claude Code can use and which require approval. Permissions are set in settings files and follow a hierarchy from user-level to project-level configuration.

Exam Context

Understand the permission model: allow, deny, or ask. Know that allowedTools in settings controls the whitelist. Project-level settings cannot override user-level denials.

PostToolUse

A hook that fires after a tool completes execution in Claude Code. Receives the tool name, input, and output. Cannot prevent execution (already happened) but can log results, trigger notifications, or perform cleanup.

Exam Context

PostToolUse hooks are for observation, not prevention. Use for audit logging, notifications, or triggering dependent workflows after tool completion.

PreToolUse

A hook that fires before a tool is executed in Claude Code. Receives the tool name and input as environment variables. Can block execution by returning exit code 2, or modify the operation. Used for validation and logging.

Exam Context

Exit code 0 allows execution, exit code 2 blocks it with feedback to Claude. The hook receives TOOL_NAME and TOOL_INPUT environment variables.

S

Settings Hierarchy

The order in which Claude Code resolves configuration: user-level (~/.claude/settings.json), project-level (.claude/settings.json), and enterprise-managed settings. More specific settings override general ones, with security exceptions.

Exam Context

User-level security settings (denied tools) cannot be overridden by project-level config. This prevents malicious repos from escalating permissions.

Slash Command

A custom command invoked with a / prefix in Claude Code. Built-in commands include /help, /clear, and /compact. Custom slash commands can be defined via .claude/commands/ directory with markdown files that serve as prompt templates.

Exam Context

Know how to create custom slash commands: place a .md file in .claude/commands/ with the prompt template. The filename becomes the command name. Arguments use $ARGUMENTS placeholder.

W

Worktree

A Git feature that allows multiple working trees attached to the same repository. Claude Code supports worktrees for parallel development: run multiple Claude Code sessions on different branches of the same repo simultaneously.

Exam Context

Know that worktrees enable parallel Claude Code sessions without conflicting file changes. Each worktree has its own working directory but shares the Git history.