#tokens

Use /effort (low→max) or CLAUDE_CODE_EFFORT_LEVEL so simple edits stay cheap and hard debugging gets deeper reasoning without paying max on every prompt.

Every installed skill spends context just being listed, before you invoke anything. Sort the list by cost, then set the ones you never use to name-only.

Instruct Claude (and yourself) to search with rg/Glob first so giant file reads do not blow the context window.

Shift specialized playbooks into on-demand skills so every session does not pay for instructions you rarely need.

Trim project memory to under ~200 lines so Claude follows critical rules instead of drowning them in noise.

Run /context to break down token consumers—CLAUDE.md, MCP tools, conversation—and prune the expensive ones.

Turn off MCP servers unrelated to the current project—their tool schemas still consume context at session start.