course contents
Developer Foundations · 3.1% of the exam
claude code
share
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.
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).
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).