Quick Reference: Domain 3 — Claude Code Configuration & Workflows

Settings are loaded in this order, with later entries overriding earlier ones:

Key rule: More specific scopes override broader ones. A directory-level CLAUDE.md overrides the project-level one for files in that directory.

Files in .claude/rules/ use YAML frontmatter with a paths field for conditional loading:

---
paths:
  - "src/api/**"
  - "src/middleware/**"
---
Always validate authentication tokens before processing API requests.
Use structured error responses with proper HTTP status codes.

Rules are loaded only when Claude Code operates on files matching the glob patterns. This prevents irrelevant rules from consuming context window space.

Skill properties:

• allowed-tools — Restricts which tools the skill can use
• context: fork — Runs in a forked context so skill execution does not pollute the main conversation

Skills are reusable capability modules. They encapsulate a workflow (e.g., "run tests", "deploy to staging") with constrained tool access.

Commands are invoked with / prefix. They are templates — predefined prompts that can include $ARGUMENTS placeholders for user input.

Difference from skills: Commands are prompt templates. Skills are capability modules with tool restrictions and isolated context.

Critical property: Hooks are deterministic — they run as code, not as model instructions. They cannot be bypassed by prompt injection or model reasoning.

Contrast with prompt instructions:

• Prompt: "Never delete production files" → Probabilistic, may be violated
• PreToolUse hook blocking rm on /prod/ paths → Deterministic, cannot be violated

Plan mode signals: The task is complex, has multiple valid approaches, or the consequences of a wrong approach are high. Plan mode forces Claude to outline its approach before executing.

-p flag: Runs Claude Code in non-interactive mode. Essential for CI/CD integration. No confirmation prompts, no interactive input — the command must be self-contained.

• Concrete examples beat prose descriptions. Show the code you want, not a paragraph describing it.
• Batch independent fixes in a single message. Sequence dependent ones (fix A, then fix B that depends on A).
• Independent review sessions: Never review code in the same session that wrote it. The model retains reasoning bias from the writing session. Start a fresh session for review.
• Severity calibration: Use examples to show what constitutes a critical issue vs. a minor style nit. Without calibration, the model treats all issues as equally important.

• Permissions are controlled at the tool level — you grant or deny access to specific tools.
• The allowedTools field in agent/skill configuration restricts the tool set.
• Principle of least privilege: Each agent/skill should have access only to the tools it needs.
• Project-level settings (.claude/) are committed and shared. Personal settings (~/.claude/) are not.