Option C applies an orchestrator-worker architecture to a request containing several distinct domains. Rather than making one agent continuously switch between billing, shipping, and product reasoning, an orchestrator can decompose the ticket, delegate each concern to an appropriately scoped specialist, track completion, and consolidate the resulting recommendations.

Anthropic describes this architecture directly: an orchestrator dynamically breaks down a task, delegates subtasks to worker agents, and synthesizes their results. Anthropic's multi-agent Research system similarly uses a lead agent that coordinates specialized subagents operating with independent contexts.

A rigid workflow is inappropriate because not every ticket contains the same combination or ordering of issues. B can improve behavior but leaves one agent responsible for managing all competing concerns and state. D increases raw context capacity without addressing decomposition or responsibility boundaries.

C is therefore the strongest architectural change when separate issue categories can be handled independently and then reconciled by a coordinating component. Relevant Study Guide topics: orchestrator-workers, subagents, delegation, task decomposition, context isolation, coordination, and synthesis.

===============

Option B creates a clear separation between persistent application instructions and per-request user content. Stable behavioral rules—role, output conventions, formatting constraints, policies, and other instructions intended to apply across requests—belong in the system-level instruction layer. User messages should primarily carry task-specific input and requirements that vary from interaction to interaction.

Anthropic’s Messages API defines the system prompt specifically as the mechanism for providing overarching context and instructions to Claude. Current guidance likewise recommends the top-level system field for instructions that should apply from the beginning of the conversation, while more transient information belongs in conversation messages.

A mixes persistent application behavior with user-controlled content and weakens separation of concerns. C preserves the inconsistent architecture responsible for the problem. D duplicates instructions unnecessarily, wastes context tokens, and increases the possibility that future edits create conflicting versions of the same rule.

Consolidating stable instructions also makes prompts easier to version, evaluate, review, and maintain. Therefore, B is the correct design. Relevant Study Guide topics: system prompts, instruction hierarchy, prompt organization, formatting consistency, separation of concerns, and maintainable prompt construction.

Option A correctly treats the MCP server as a reusable integration boundary rather than application-specific code. Model Context Protocol separates capability providers from consuming Claude applications by exposing standardized tools, resources, and prompts through an MCP-compatible interface. A shared server therefore needs explicit capability definitions, an appropriate transport or communication pattern, and a deployment location reachable by its intended clients.

Anthropic’s MCP documentation distinguishes remote HTTP-based integrations from local/client-managed connections. For remotely shared services, the server must be reachable from the consuming environment; client-side MCP helpers additionally support broader MCP capabilities such as resources and prompts.

B unnecessarily couples the server design to the first consumer and encourages application-specific evolution of what should be a reusable service boundary. C prevents multi-application deployment because only local developer sessions could reach the service. D abandons MCP entirely and recreates duplicated integrations in every consuming application.

Thus, A provides the correct lifecycle: define the MCP contract, expose resources/tools/prompts appropriately, select the transport according to topology, deploy the service, and let multiple applications consume the standardized interface independently. Relevant Study Guide topics: MCP architecture, reusable services, tools, resources, prompts, transports, and deployment topology.

===============

The supplied question marks C , and Anthropic's API documentation directly supports it. Claude API rate limits are enforced using dimensions such as requests per minute (RPM), input tokens per minute (ITPM), and output tokens per minute (OTPM) . Anthropic also notes that short traffic bursts can exceed effective limits even when a longer-term average appears acceptable.

Applications should therefore determine the organization's actual configured limits, model peak traffic against those boundaries, throttle or queue work as necessary, and handle 429 responses correctly. Rate-limit responses include a retry-after value indicating when another request should be attempted. Anthropic's official SDKs automatically retry transient connection failures, rate-limit errors, and server errors with exponential backoff by default.

Streaming does not exempt requests from rate limits, making A technically incorrect. Consolidating payloads in B may reduce request count but could increase token consumption and does not by itself address all rate-limit dimensions. D may smooth traffic, but it is only one optimization and does not substitute for rate-limit-aware application logic.

Relevant Claude Developer topics: Claude API Mechanics, rate limits, RPM, ITPM, OTPM, HTTP 429, retry-after, exponential backoff, throttling, and capacity planning .

===============

The supplied Claude Developer examination source selects A . The purpose of choosing an agent SDK rather than implementing a custom Messages API loop is to consume the SDK's higher-level abstractions. Re-implementing dispatch, iteration, and state handling would discard much of the value provided by the SDK.

Anthropic's current documentation distinguishes low-level tool-use loops from higher-level SDK-managed abstractions. With a manually implemented Messages API workflow, application code must inspect stop_reason, execute requested client tools, append tool_result blocks, preserve conversation history, and repeat until Claude completes the turn. Anthropic's higher-level tooling can instead encapsulate this repetitive control flow. Current migration guidance also confirms that Agent SDK @tool functions are automatically dispatched by the SDK and that agents, tools, and sessions are first-class SDK concepts.

B is incorrect because structured tool use should not be replaced with informal plain-text calls. C introduces an unnecessary custom state dependency when no external persistence requirement exists. D duplicates control-loop functionality despite the explicit decision to use the SDK.

Relevant Claude Developer topics: Agent SDK, tool definitions, dispatch, agentic loops, conversation state, tool execution, and abstraction selection .

===============

Option D applies the correct hybrid pattern. Anthropic distinguishes workflows—where LLMs and tools execute along predefined code paths—from agents, where the model dynamically determines how to proceed. Anthropic recommends choosing the simplest architecture that meets the requirement: workflows provide predictability and consistency for well-understood tasks, while agents are valuable where flexible model-driven decisions are necessary.

Standard invoice processing is explicitly described as a small number of known steps. That makes a deterministic workflow the appropriate default because the path can be tested, monitored, and reproduced. The unexpected-format branch is different: the system must reason among rerouting, requesting clarification, or human escalation. That decision point is where agentic flexibility adds value.

A makes the entire process autonomous even though most steps do not require autonomy, increasing cost, latency, and unpredictability. B introduces multiple specialized agents despite no demonstrated need for that complexity. C collapses deterministic processing and exception handling into one monolithic model call, making validation and debugging harder.

Therefore, D combines workflow predictability with targeted agentic reasoning. Relevant Study Guide topics: workflows versus agents, routing, exception handling, hybrid agentic architecture, escalation, and complexity minimization.

===============

Option D is directly supported by both the supplied examination material and Claude Code's MCP documentation. The examination source selects STDIO for this local-process scenario.

Claude Code's official MCP guidance distinguishes remote HTTP servers from local STDIO servers . Anthropic states that STDIO servers run as local processes and communicate through standard input and standard output. They are particularly suitable for local tools requiring direct machine access or for custom scripts. Claude Code can launch the process itself and communicate with it without creating, exposing, securing, or maintaining a network listener.

HTTP is appropriate when the MCP server exists as a separately reachable network service, especially for cloud-hosted or shared services. That requirement is absent here: the server is being invoked locally from a Claude Code session.

A creates duplicate transport infrastructure without a stated availability requirement. B incorrectly assumes one transport is universally superior regardless of deployment topology. C describes HTTP polling rather than the normal MCP transport relationship and introduces unnecessary request overhead.

Therefore, local execution strongly favors STDIO; remote/shared deployment generally favors HTTP.

Relevant Claude Developer topics: MCP architecture, STDIO transport, HTTP transport, Claude Code integrations, local process communication, and deployment topology .

===============

Option C applies the appropriate context-management technique. The issue is not simply whether the older conversation can physically fit into the context window; it is that stale details remain prominent enough to interfere with the model’s current task. Effective context engineering optimizes signal quality, not merely maximum token retention.

Anthropic’s context-editing documentation describes compaction as summarizing accumulated history and replacing the full history with a structured summary when context becomes large. This preserves important task state while substantially reducing low-value detail that can distract later reasoning.

A retains precisely the stale material producing the problem and therefore does not address context drift. B destroys all useful continuity between turns, including valid goals, decisions, and intermediate state. D is similarly excessive because limiting Claude to only the latest turn discards information that may still be required.

Compaction provides the correct middle ground: retain durable conclusions, current objectives, unresolved issues, and other high-signal state while compressing obsolete conversational detail. Relevant Study Guide topics: context engineering, compaction, conversation history, long-running agents, stale context, context drift, and high-signal state preservation.

===============

Option C matches Claude Code’s documented Skill architecture. Agent Skills are filesystem-based extension artifacts rather than ordinary application modules or repeated prompt fragments. A Skill is represented by a directory containing a required SKILL.md file and can include optional supporting scripts, templates, examples, and reference material.

Anthropic documents project Skills under .claude/skills/ < skill-name > /SKILL.md. Project-level Skills can be shared through Git and automatically discovered when Claude Code loads project settings. Supporting scripts can reside alongside the Skill and be referenced from SKILL.md.

A incorrectly embeds reusable procedural material into every CLAUDE.md file, creating duplication and loading instructions even when they are irrelevant. B creates a conventional source-code library but does not register a Claude Code Skill. D makes the capability dependent on undocumented, developer-specific setup and undermines team reuse.

Therefore, C uses the extension mechanism specifically designed for discoverable, reusable Claude capabilities. Relevant Study Guide topics: Agent Skills, .claude/skills, SKILL.md, supporting resources, filesystem discovery, project-level configuration, and reusable Claude Code capabilities.

===============

Option D is the strongest enforcement design because an unconditional content policy requires an application-level control between model generation and user delivery. Prompt instructions are valuable for steering Claude, but they are probabilistic controls and should not be treated as the sole enforcement mechanism when prohibited categories must never be exposed.

Anthropic’s guardrail guidance recommends layered safeguards including screening, validation, monitoring, and filtering rather than relying exclusively on prompts. Its prompt-leak guidance specifically recommends output screening and post-processing, including deterministic techniques such as keyword matching, regular expressions, or other text-processing mechanisms where appropriate.

A improves the probability of policy compliance but cannot guarantee that every generated response will satisfy an externally defined application policy. B explicitly abandons the requirement. C detects violations only after exposure, which is unsuitable when the content must not reach users.

A production architecture can combine system instructions, structured classification, policy engines, deterministic rules, and model-based moderation, but the decisive requirement is enforcement before output delivery. Relevant Claude Developer topics are guardrails, output filtering, content moderation, deterministic enforcement, defense in depth, safe application boundaries, and production Claude application design.

===============