The whole hunk
from line 1580, old and new numbered
/
lines
from line 1580
15801580
15811581The session walks through a realistic flow with representative token counts:
15821582
1583* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. Your own setup may add more here, like an [output style](/docs/en/output-styles) or text from [`--append-system-prompt`](/docs/en/cli-reference).
1583* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on their own or alongside CLAUDE.md. Your own setup may add more here, like an [output style](/docs/en/output-styles) or text from [`--append-system-prompt`](/docs/en/cli-reference).
15841584* **As Claude works**: each file read adds to context, [path-scoped rules](/docs/en/memory#path-specific-rules) load automatically alongside matching files, and a [PostToolUse hook](/docs/en/hooks-guide) fires after each edit.
15851585* **The follow-up prompt**: a [subagent](/docs/en/sub-agents) handles the research in its own separate context window, so the large file reads stay out of yours. Only the summary and a small metadata trailer come back.
15861586* **At the end**: `/compact` replaces the conversation with a structured summary. Most startup content reloads automatically; the table below shows what happens to each mechanism.