Learn
How coding agents read your instructions
Short explainers, checked against each vendor's own documentation. New to the vocabulary? The glossary has one-line definitions.
What is CLAUDE.md?
CLAUDE.md is a plain markdown file of instructions that Claude Code reads at the start of every session. Here's where it lives, how it loads, and how long it should be.
Verified 2026-09-19
AGENTS.md vs CLAUDE.md: which one do you need?
AGENTS.md is the shared instruction file most coding agents read; CLAUDE.md is Claude Code's own. Here's which tools read which, and how to keep one set of rules for all of them.
Verified 2026-09-19
How MCP servers add to your agent's context
Every MCP server you enable gives your coding agent tools — and every tool has a description and schema the model has to read. Here's how that adds up and how to keep it down.
Verified 2026-09-19
How to reduce Claude Code costs
The biggest levers on Claude Code spend, from Anthropic's own guidance: clear context between tasks, pick the right model, keep CLAUDE.md short, and watch prompt-cache expiry.
Verified 2026-09-19