Prompt

"Look, don't touch": /readonly on blocks edits and every command that is not provably read-only, and tells Claude to investigate and explain instead.

Keeps credentials out of your code, your shell commands and Claude's context: blocks hard-coded secrets in edits, asks before commands with literal keys, redacts secrets from tool results and flags them in prompts.

Opt-in: questions about the codebase (where is, what does, how does, which file, find) go to a read-only haiku scout subagent first; its answer comes with Ask Claude anyway and Good enough, and the tokens saved.

Opt-in: after a turn that adds or changes functions, sonnet (or haiku) drafts focused unit tests in the background, in the repo's framework and style; Review, Add & run (only that file), or Dismiss; never writes without a press; daily budget cap.

Spend tracking across sessions: session and today's cost in the status line, daily and weekly budgets with toasts and an optional hard stop, and a /spend pane.

A one-line TL;DR under long answers, written by haiku.

Your commit and pull request credit line, your way: Claude Code's default, none, or your own template with {model}.

Per-prompt effort autopilot: classifies each prompt (Jev, Claude Haiku, or heuristics) and sets that turn's effort, and optionally its model, only when the switch beats the prompt-cache rewrite it causes.

Asks before sending a huge pasted log, stack trace, JSON or CSV: shrink it to a digest (head, tail, error lines) and save the full text under .claude/pastes, or send it as is.

See the system prompt section by section with sizes, and switch sections off for a project.

See the reminders and notices Claude Code injects for the model, by type and size, and mute the ones you do not want.