You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution.
You've documented API error handling conventions in a CLAUDE.md file at your project root, specifying that endpoint handlers should use a custom ApiError class. After several sessions, you notice Claude Code sometimes follows these conventions and sometimes uses generic try/catch blocks with string messages. The inconsistency appears random across different coding sessions. What's the most efficient first diagnostic step?

• A. Create path-specific rules in .claude/rules/handlers.md with YAML frontmatter scoping the error handling instructions to your API handler files.
• B. Search for conflicting instructions in ~/.claude/CLauDe.md or ~/.claude/rules/ that might override your project conventions.
• C. Run /memory to check which memory files are loaded and verify your CLAUDE.md is included.
• D. Add a more detailed code examples to your CLAUDE.md showing the exact ApiError usage pattern for different endpoint types.

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools ( get_customer, lookup_order , process_refund , escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.
After expanding the agent's MCP tools with delivery-specific capabilities ( check_delivery_status , contact_driver , issue_credit , apply_promo_code , update_delivery_address , reschedule delivery ), the total tool count has grown from 4 to 10. Your evaluation suite shows tool selection accuracy has dropped from 88% to 71%. Log analysis reveals the majority of errors involve the agent selecting between semantically overlapping tools - calling issue_credit when process_refund was correct, and calling check_delivery_status when lookup_order already returns the needed data. Which approach structurally eliminates the semantic overlap identified in the logs as the error source?

• A. Add few-shot examples to the system prompt demonstrating correct selection for each ambiguous tool pair, such as showing when issue_credit applies versus when process_refund is appropriate.
• B. Consolidate semantically overlapping tools - merge issue_credit and process_refund into a single resolve_compensation tool with an action parameter, and fold check_delivery_status into lookup_order with an optional include_tracking flag.
• C. Enable the tool search tool with defer_loading on the six new tools, keeping the original four always loaded, so the agent dynamically discovers specialized tools only when needed.
• D. Split the tools across two sub-agents - a "financial resolution" agent with process_refund , issue_credit ,and apply_promo_code , and a "delivery operations" agent with the remaining delivery tools - with a coordinator routing between them.

After 30+ turns, your conversational assistant shows noticeably slower responses and occasionally produces less coherent outputs. Investigation reveals: (1) average conversations reach 50,000 tokens by turn 35, (2) production logs show 94% of user messages only reference the previous 3-5 exchanges, (3) the 6% of queries referencing earlier context typically ask about information the user could easily re-state. Your goal is to improve response speed and quality while maintaining good user experience. What's the most effective approach?

• A. Enable prompt caching and continue sending the complete conversation history, using cached prefixes to reduce per-request costs while preserving all context.
• B. Build a retrieval system that stores all conversation turns and uses semantic search to pull in relevant historical context only when the current query appears to reference past information.
• C. Implement a summarization layer that progressively compresses older conversation turns into a running summary while keeping the most recent 5-6 turns verbatim, maintaining full historical context in condensed form.
• D. Implement a sliding window keeping only the system prompt and last 8-10 turns. When users reference earlier context, acknowledge the limitation and ask them to re-state the relevant information.

The web search agent has gathered several relevant sources for a research topic. The document analysis agent now needs to examine these sources. How does information typically flow between these two specialized subagents?

• A. The web search agent directly invokes the document analysis agent, passing the discovered sources as parameters.
• B. Both agents access a shared memory store where the web search agent writes findings and the document analysis agent reads them.
• C. The coordinator agent receives the web search agent's output and includes relevant findings in the prompt when invoking the document analysis agent.
• D. The agents communicate through an event-driven message queue, with the document analysis agent subscribing to web search completion events.