Page 2 of 3
Instruct Claude (and yourself) to search with rg/Glob first so giant file reads do not blow the context window.
Enable auto mode so a classifier approves safe tool calls and blocks destructive ones — fewer prompts without a full permission bypass.
Run prettier/ruff/gofmt automatically after Edit/Write tools so Claude never leaves unformatted files.
Cycle into plan mode (Shift+Tab) so Claude explores and proposes an approach for approval before editing.
A skill that checks a link or reformats a file does not need your session model. Set model, effort and context: fork in the frontmatter so cheap skills stay cheap.
Put domain-specific instructions in path-scoped `.claude/rules/` so they load only when Claude touches matching files.
Build slash skills that accept issue numbers, branch names, or formats via $ARGUMENTS / $0 so one command covers many cases.
Use `claude --worktree` (or git worktrees) so multiple agents edit isolated checkouts without colliding.
Add a Notification hook that plays a short sound when Claude is idle or waiting on permission so you can multitask without staring at the terminal.
Shift specialized playbooks into on-demand skills so every session does not pay for instructions you rarely need.
Claude Code re-reads your whole conversation at the cached rate. Come back after a long lunch and the first message reprocesses all of it at full price.
Trim project memory to under ~200 lines so Claude follows critical rules instead of drowning them in noise.
Define custom subagents with `isolation: worktree` so delegated edits happen on a temporary branch checkout.
Run /context to break down token consumers—CLAUDE.md, MCP tools, conversation—and prune the expensive ones.
Add a deterministic PreToolUse hook that rejects destructive shell patterns before Claude can run them.
Use `claude --print --output-format json` in GitHub Actions to automate reviews or summaries without an interactive TTY.
When a skill hits an edge case, append it to a gotchas section in that skill rather than to CLAUDE.md. The lesson then loads only when the skill runs.
Write the tests first, then set the goal to making them pass. Claude keeps working across turns until the condition is met instead of stopping after each reply.
Add the GitHub MCP server so Claude can cross-reference issues, PRs, and repo state without leaving the session.
Instead of guessing which commands to allowlist or giving up and skipping permissions entirely, let Claude read your past sessions and propose the rules you have already been approving.
Use /config to set Explanatory or Learning output style so Claude explains the why behind changes — not just the diff.
Enable /memory auto-memory so Claude writes durable notes about build commands, corrections, and patterns that reload on every new session.
Use the bundled /doctor skill to find duplicate local memory, unused MCP/plugins, and slow hooks eating budget.
Turn off MCP servers unrelated to the current project—their tool schemas still consume context at session start.