Status line

A tiny Claude to raise while you work: feed it your edits, play, clean, dress it up, watch it evolve.

Shows your Claude 5 hour and weekly rate limits in the status line and warns at 80% and 90%.

Stops Claude from starting a second copy of your dev servers on the next free port (monorepos and worktrees included), tracks the servers it starts, and stops leftovers from a /procs pane.

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

Keep the model fixed and pick the reasoning effort per turn by classifying the prompt with $.model.classify

Route each turn to Haiku / Sonnet / Opus with TypeSafe Jev (default: Sonnet)

Shows the OpenSpec changes of the open project under the prompt, for local roots and stores.

Masks the values from ~/.claude/secrets/*.env in everything the model reads

Oculta a Claude los datos personales (DNI, NIE, IBAN, teléfonos, emails, claves) cambiándolos por falsos válidos y los restaura al ejecutar, todo en tu máquina

Cierre ordenado antes de quedarse sin contexto, sin cuota o sin caché: escribe un documento de traspaso y el prompt para seguir en otra sesión, y avisa al móvil

在每段回复下加一个🔊按钮，用火山引擎豆包语音（知性女声 2.0）流式朗读，可暂停、继续、从头念、倍速

Opens a card when Claude's final answer omits a recorded file change or a recognized command with side effects, or makes a test or Git claim the recorded results do not fully back. Step through the diffs and prepare an editable question.

Context window fill in the status line, with a heads-up before it runs out

Pane of token and USD spend: this session, today, last 7 days

Shows each running subagent's model and effort on the hint line above the agent list

コンテキスト残量とプランの使用量をステータス行に常時表示する

Dry-runs risky Bash commands (recursive deletes, destructive git, kubectl delete, SQL wipes) and asks Proceed or Cancel first.

Plays Subway Surfers gameplay in a pane while Claude works

A pane and toasts for background shells, monitors and subagents: status, elapsed time, latest output line, exit code

Bleach: un Bankai animado al azar cuando una tarea sale bien, colección con /bankai, y hollowificación según el contexto usado

Rewrite a prompt with Sonnet 5.5 (high effort) and put it back in the prompt box for review: end it with ' ++' or use /enhance

Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top three with their SKILL.md and can reject them all. The winner's...

Shows context fill, 5-hour and weekly quota, and session cost on the status line under the prompt, with warnings near your limits.

Gates git work: no commit, push or merge without the user's say-so in their latest message; a push to a branch that already landed is refused; a pushed series must leave the project working at every commit; commit messages (format and the issue it is about, then a Haiku review of the body) and MR descriptions kept tidy.