context-optimization

To optimize context for multi-agent conversations, use targeted @ mentions to reference files and docs directly instead of duplicating content. This approach preserves critical information across long-running tasks while keeping context strictly within token limits.

Semantic search for retrieving code references works by providing strategies for efficient information retrieval in large codebases. It guides AI agents to locate and reference relevant code sections directly, reducing unnecessary prompts and minimizing token usage during multi-agent conversations.

Yes, context optimization is designed for multi-agent conversations and long-running tasks. It centralizes how AI systems manage contextual data, satisfying frontmatter requirements and providing reference guidance to control prompts and preserve relevant information across extended workflows.

Keeping AI context within token limits while preserving critical codebase information is achieved through context window optimization. By using concise references and controlled prompts, the skill reduces unnecessary data duplication and maintains only the relevant information needed for the task.