context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool permissions — The rules governing which tools an agent may call and which need confirmation — the boundary between a mistake and an incident.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
It's the canonical, vendor-authored playbook for getting real work out of Claude Code — concrete guidance on CLAUDE.md context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → files, tool permissionsThe rules governing which tools an agent may call and which need confirmation — the boundary between a mistake and an incident.Full definition →, custom slash commands, and running multiple AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → sessions in parallel. Worth reading before you copy someone else's tips list, since third-party guides are largely derived from it.
Key quotes
“Most best practices are based on one constraint: Claude’s context window fills up fast, and performance degrades as it fills.”
“Give Claude a check it can run: tests, a build, a screenshot to compare.”
“If you could describe the diff in one sentence, skip the plan.”
“A clean session with a better prompt almost always outperforms a long session with accumulated corrections.”
