Developer Foundations · 3.1% of the exam

claude code

This domain is about one scored question in thirty, and it has one objective: operating Claude Code itself, from the files a session finds at launch to runs that a script starts with no one watching.

Course example

This domain keeps following Shelfwise, the internal stock-question tool: a long-lived Python service built on the Agent SDK, the Anthropic library that runs Claude in a tool loop, whose agent answers shop staff from one stock feed through stock_mcp, its one MCP server, a program that offers tools to Claude applications over MCP, the Model Context Protocol.

In Domain 3 the three engineers run Claude Code on Shelfwise's own repository, to add branches and to fix the stock-feed client. Adding a shop's branch becomes a script, scripts/add_branch.sh, that runs Claude Code with no one at the keyboard: it names its permission mode and its one allowed test command, and it fails if any action was denied (3.1).

claude -p: one task, then exit--permission-mode acceptEdits--allowedTools: the test commandstream-json: fail on any denial
0 files changedby the script's first version, which set no permission mode and still exited 0. The run started in Manual mode on the engineers' accounts, and with nobody there to answer, each edit prompt was denied. The fixed script names the mode, and the committed push guard from 7.3 still runs.

Start hereThe words used throughout this domain

context window
The most text that one request to Claude can hold: instructions, the conversation so far, tool results and room for the reply (6.1).
CLAUDE.md
A Markdown file of instructions you write, which Claude Code loads into every session as context, not as enforced configuration (2.6).
Skill, SKILL.md
A folder of instructions built around SKILL.md, whose short description lets Claude match a task to it and whose body loads only when used (2.5, 8.3).
subagent
An agent another agent starts for one subtask. It works in its own context window and returns only its final message (1.1).
hook, PreToolUse
Your own code that runs at a fixed event in Claude's agent loop. A PreToolUse hook runs just before a tool call and can block it; Claude Code reads hooks from settings files (1.2, 7.3).

task statements

flashcards

0 / 3 known
Card 1 of 3