An application frequently repeats the same background instructions in every API request. What is a potential downside?

• A. Increased hallucinations only.
• B. Reduced model capability.
• C. Higher token usage and cost.
• D. Lower reliability.

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.
Your code review assistant needs to analyze pull requests and provide feedback on three aspects: code style compliance, potential security issues, and documentation completeness.
Each aspect requires reading files, running analysis tools, and generating a report section. The review process follows the same three-step workflow for every PR. Which task decomposition pattern is most appropriate for this workflow?

• A. Single comprehensive prompt - include all instructions in one prompt and let the model handle all three aspects simultaneously.
• B. Orchestrator-workers - have a central LLM analyze each PR to dynamically determine which checks are needed, then delegate to specialized worker LLMs for each identified subtask.
• C. Routing - classify each PR by type (feature, bugfix, refactor) first, then route to different review prompts optimized for that category.
• D. Prompt chaining - break the review into sequential steps where each aspect (style, security, documentation) is analyzed separately, with outputs combined in a final synthesis step.

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.
An engineer asks the agent to find all files in the monorepo that import the @company/auth package to understand how authentication is used across services. Which built-in tool is most appropriate for this task?

• A. Bash, to execute find. -type d -name "*auth*" and explore matching directories
• B. Grep, to search for the import statement pattern across file contents
• C. Read, starting with package.json files to trace dependency declarations
• D. Glob, to find files with "auth" in their filename or path

You've configured the system so that all four subagents have access to the complete set of
18 tools. During testing, agents frequently call tools outside their specialization - the synthesis agent attempts web searches, and the report generator tries to analyze documents. What is the primary cause of this poor tool selection behavior?

• A. The tool definitions consume too much context window space, leaving insufficient room for task content.
• B. The agents' role descriptions in their system prompts conflict with having access to tools outside that role.
• C. The coordinator cannot track which capabilities each subagent has, leading to misrouted tasks.
• D. Choosing from 18 tools instead of 4-5 relevant ones increases decision complexity beyond reliable selection thresholds.

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.
An engineer used the agent yesterday to analyze a legacy authentication module, identifying two distinct refactoring approaches: extracting a microservice versus refactoring in-place. Today, they want to explore both approaches in depth - having the agent propose specific code changes for each - before deciding which to implement. What's the most effective way to structure this exploration?

• A. Resume yesterday's session and explore both approaches sequentially within the same conversation thread.
• B. Start two fresh sessions, manually providing a summary of yesterday's analysis findings to establish context.
• C. Resume yesterday's session to explore the first approach, then start a new session for the second, manually recreating the original context.
• D. Use fork_session to create two branches from yesterday's analysis, exploring one approach in each fork.