Claude Code Made Crystal Clear · chapter 2: Core Concepts: The Agentic Loop and the Context Window
The map of the machine
2026-09-07
One session sits at the center with its context gauge. Inputs fill the context from the left, actions flow out through the guards to the actuators on the right, and their results loop back in as new context. Subagents orbit with context windows of their own. Later chapters zoom into one region at a time.
Below: the paragraph from the book that builds this idea, then the diagram itself (Figure 2.2), and a recap. About a minute of reading.
You now have both core models: a loop that acts, and a finite window it must live in. Every feature Claude Code ships (CLAUDE.md, skills, hooks, MCP, subagents, permission modes) plays one of five roles around that pair. Figure 2.2 is the master schema of this book. Later chapters do not introduce new machinery; they zoom into one region of this diagram at a time.
Recap
- The idea: One session sits at the center with its context gauge.
- The picture: Figure 2.2, from chapter 2 ("Core Concepts: The Agentic Loop and the Context Window") of Claude Code Made Crystal Clear.
- Go deeper: the chapter builds this step by step, with recipes and sources at the end.
This diagram is one of many in Claude Code Made Crystal Clear.
Every chapter opens with the gist, draws the hard ideas, and ends with recipes and sources.
Get the book
