Understanding LLMsThrough Claude Code

Understand the structural constraints of LLMs and learn "why" configurations are designed the way they are.

Start Reading

View on GitHub

Part 1: Structural Problems

The 8 limits LLMs cannot overcome by themselves — Context Rot, Lost in the Middle, Hallucination, and more.

Part 2: Context Window

The LLM's thinking space — tokens, context budget, and injection timing.

Part 3: Always-Loaded Context

CLAUDE.md design, hierarchical merging, and CLAUDE.local.md.

Part 4: Conditional Context

Rules and glob patterns — context loaded only when files match.

Part 5: On-Demand Context

Skills and Agents — context loaded only when the LLM asks for it.

Part 6: Tool Context — MCP

Tool definitions as context cost, and how Tool Search avoids it.

Part 7: Runtime Layer

settings.json and Hooks — the layer LLMs never see.

Part 8: Session Management

/compact, /clear, and what to persist across sessions.

Part 9: Code Intelligence

LSP-driven grounding for code symbols — the second pillar alongside MCP.

Part 10: Multi-Session Coordination

Agent Teams as the root-cause fix for Context Rot at scale.

Part 11: Cross-LLM Principles

Universal patterns that apply to Cursor, Cline, Copilot, and beyond.

Appendix

Maps, configuration reference, FAQ, plugins, and glossary.

📚 Sister Projects

A 3-phase learning path: "Know LLMs → Know Agent Design → Apply to Systems."

Phase	Project	Focus
1. Know LLMs	👈 This site	LLM structural constraints and the why behind configuration design
2. Know Agent Design	ai-agent-architecture	MCP, Skills, and Agent composition with implementation patterns (what/how)
3. Apply to Systems	Management-of-software-systems-and-services	Coming soon — System operations in the AI era

TIP

For readers who learned the "why" here — for concrete implementation patterns (MCP catalog, Skills design, Agent taxonomy, A2A protocol, etc.), read the sister site ai-agent-architecture alongside this one to connect the why with the how.