S4 · scenario126 questions · 25 free
Developer productivity tools (S4)
Agents that explore codebases and automate tasks with built-in tools + MCP.
This scenario spans 18 subtopic areas, covered by 126 practice questions across 28 easy, 70 medium, and 28 hard items.
Sample question · free
Your developer productivity agent runs Grep to locate a symbol, then issues a Read call. The API returns stop_reason 'tool_use' after the Read response is sent. What does this tell the loop?
What's covered
Subtopic areas in Developer productivity tools, drawn from the exam blueprint:
1.1Design and implement agentic loops for autonomous task execution91.2Orchestrate multi-agent systems with coordinator-subagent patterns61.3Configure subagent invocation, context passing, and spawning81.4Implement multi-step workflows with enforcement and handoff patterns81.5Apply Agent SDK hooks for tool call interception and data normalization71.6Design task decomposition strategies for complex workflows81.7Manage session state, resumption, and forking72.1Design effective tool interfaces with clear descriptions and boundaries82.2Implement structured error responses for MCP tools72.3Distribute tools appropriately across agents and configure tool choice72.4Integrate MCP servers into Claude Code and agent workflows52.5Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively63.1Configure CLAUDE.md files with appropriate hierarchy, scoping, and modular organization63.2Create and configure custom slash commands and skills63.3Apply path-specific rules for conditional convention loading83.4Determine when to use plan mode vs direct execution83.5Apply iterative refinement techniques for progressive improvement73.6Integrate Claude Code into CI/CD pipelines5