Page 3 of 3
Use /config to set Explanatory or Learning output style so Claude explains the why behind changes — not just the diff.
Mark deploy/ship/destructive skills so only an explicit /command runs them—Claude cannot auto-trigger them mid-session.
Claude Code deletes session files older than 30 days at startup. If you have ever gone looking for a session you know you had, this setting is why it was gone.
Use /permissions to allowlist read-only and trusted commands so you stop mindlessly clicking Approve.
Run prettier/ruff/gofmt automatically after Edit/Write tools so Claude never leaves unformatted files.
Put domain-specific instructions in path-scoped `.claude/rules/` so they load only when Claude touches matching files.
Claude Code adds a Co-Authored-By trailer to commits and an attribution line to pull requests. Set both to empty strings and it stops.
Use `claude --print --output-format json` in GitHub Actions to automate reviews or summaries without an interactive TTY.
Inspect `/usage` (alias `/cost`) for per-skill, subagent, and MCP breakdowns, then cut the expensive outliers.
Ask Claude to log architecture decisions and TODOs into a repo file that can be re-read after /compact.
Turn on `/sandbox` so OS-level filesystem and network boundaries replace many per-command Bash prompts.
Use the bundled /doctor skill to find duplicate local memory, unused MCP/plugins, and slow hooks eating budget.
Run `/batch` on large mechanical migrations so Claude decomposes work and spawns per-unit worktree agents with PRs.
Keep personal shortcuts and machine-specific notes in CLAUDE.local.md (gitignored) instead of polluting the shared CLAUDE.md.
Instruct Claude (and yourself) to search with rg/Glob first so giant file reads do not blow the context window.
Cron a useful headless Claude task each morning: failing CI, stale PRs, and TODO hotspots—not an empty warmup.