All mods

Replaces Claude Code's core system prompt with pi's coding agent prompt; /pi-prompt toggles it, remembered across sessions.

A minimal footer under the prompt: busy or idle, project directory and git branch, context usage, model and effort.

Shows what Claude is running and adding to the model's context, the way pi does: every tool call on its own row, the end of Bash output, how long each call took, injected context, and a spinner naming the running call.

Una línea fina encima del prompt con el uso de los límites de 5 horas y semanal

Una línea fina encima del prompt con el uso de los límites de 5 horas y semanal

/purgar: quita del contexto las salidas viejas de herramientas, sin resumen y sin gastar modelo; /purgar N deja solo los últimos N intercambios

Al parar de escribir 2 s, propone el prompt de tu librería que encaja con lo que llevas escrito

A live cartoon under the spinner: Clawd acts out and narrates each step of the agent's work, drawn by Sonnet and run in a sandboxed scene language

Formats and lints every file Claude Code edits, reported as one collapsible line.

The images Claude reads, writes or makes, and the ones you paste, as a film strip right in the chat: a grey line to unroll, a viewer to browse, a develop under a red safelight (kitty graphics: Ghostty, kitty).

Your claude agents list in a side pane, with optional cones columns

Stacked context-window bar above the prompt, colored like /context; toggle with /context-bar

Live deadline countdowns in the Claude Code status line. /ddl to list, add, remove.

A control room above the prompt: background agents and shells (running, done, failed), blocked tool calls and context usage. /monitor pins it.

Usage bars (context, 5h, 7d, cost) above the prompt plus an auto-compact nudge; toggle with /usage-bar

Capi the capybara teaches you a language above the prompt, one real-world fact per card

A status bar above the prompt (context, plan limits, the running turn's time and tokens), and a frame around each final answer

Banda de estado en píldoras sobre el prompt: límites 5h/7d con cuenta atrás, contexto y tokens ↑↓ y caché. Avisos al 80% y 95%. Necesita function hooks (acceso anticipado).

Right-side pane that follows the current prompt: plan steps, tool actions and Claude's visible notes, cleared on each new prompt

Shows your homedot agents in Claude Code's status line (running, resting, stopped), with the 5-hour limit and minutes until it resets, plus a /dots pane.

Study companion: lessons and flashcards from your chats and interests, scheduled with FSRS or SM-2 spaced repetition

A one-line usage bar above the prompt: 5-hour, weekly and per-model plan limits with reset countdowns, plus the session's tokens and cost.

Animated desktop notifications when a session starts, a turn finishes, a tool fails, the context fills up, or Claude asks for permission. Nothing extra to install.

An idle game that runs beside Claude Code, fed only by the work Claude does for you