Architect Foundations · 20% of the exam

claude code configuration and workflows

Domain 3 is about the files around Claude Code: what Claude reads before you type anything, which instructions reach your teammates, and when a task should be planned first.

The scenario this domain runs on

You are using Claude Code to accelerate software development. Your team runs it every day for code generation, refactoring, debugging and documentation, in a monorepo with packages/web, packages/api and packages/infra that everyone clones from version control. You maintain the team's CLAUDE.md files, rules, custom slash commands and skills, and you decide when a task needs plan mode and when direct execution is enough.

The configuration surface you are responsible for:

CLAUDE.md.claude/rules/.claude/commands/.claude/skills/plan mode
45 filesin the library migration this team is about to start. If the configuration is wrong, the engineer doing the migration works from the wrong instructions, or from none, and Claude edits all 45 files that way before anyone notices.

Each of the six sections below is a different way that happens, from an instruction that sits in a file a teammate never receives to a CI run that cannot see what it needs.

Scenario switchSection 3.6 moves to a second scenario, the guide's Claude Code for Continuous Integration. There Claude Code runs with nobody at the keyboard, reviewing each pull request's diff, proposing tests and posting comments that the pipeline parses as JSON. It is the only section in this domain that does, and it is flagged again there.

Start hereThe words this domain is built on

CLAUDE.md
A file of standing instructions that Claude Code loads by itself, at launch from the launch directory upward, and from a subdirectory when Claude reads a file there.
Rule (.claude/rules/)
An instruction file in .claude/rules/ that loads at launch or, with a paths field, only when Claude reads a matching file.
glob
A filename pattern such as **/*.test.tsx, which a rule lists in paths.
Skill (SKILL.md)
A folder holding a SKILL.md file, whose one-line description is always in context while its body loads on demand.
Slash command
A markdown file in a commands/ directory whose body becomes the prompt when you type its name, such as /review. Claude Code has since merged commands into skills.
Scope
Where a configuration file lives: project scope reaches everyone who clones, and user scope stays on your machine.
Plan mode
A permission mode in which Claude proposes a plan but edits nothing until you approve it.
Frontmatter
The YAML block between --- lines that configures a rule or skill.
Context cost
Tokens loaded before your first message, which anything loaded at launch costs in every session.
Subagent
A separate Claude session with its own context window, which returns only its result.
Explore subagent
A built-in, read-only subagent that searches code and returns a summary.
hook and MCP
A hook is your code, which Claude Code runs at a fixed point such as before a tool call, and MCP, the Model Context Protocol, connects it to outside tools.
--resume and --continue
Flags that reopen an earlier session with its full history, which 3.6 says a CI review must not use.
Two questions sit underneath most of this domain. Who should get the instruction decides its scope: a committed file for everyone who clones, or ~/.claude/ for you alone. When it must be in context decides the file.
In every sessionThe root CLAUDE.md, or a rule with no paths field.
When Claude works inside one directoryA CLAUDE.md in that directory, or a rule whose glob names it.
For one file type, wherever it livesA rule whose paths glob matches that type.
When someone runs itA skill, or a slash command.
An instruction that loads too often costs tokens in sessions that never use it, and one that loads too rarely never reaches Claude when it matters.

task statements

flashcards

0 / 18 known
Card 1 of 18