Prompt

Clawd in pixel art under the spinner while Claude works, with a twinkling progress backdrop

When a turn ends, suggests up to three next prompts from the conversation, your open GitHub issues and pull requests, or your Linear issues.

Blocks reads of .env files and printing of API keys, with a red warning above the prompt.

Live token & USD observatory for Claude Code: per agent, subagent, workflow, task, skill and model, with prompt-cache countdowns, a model lock while the cache is warm, and subscription leverage

A side pane that keeps a TL;DR of what this Claude window is working on, refreshed after each turn from the cached transcript

/incremental: the Claude mascot mines a rock for ore; every ore is tokens

利用上限（5時間枠と週の枠）の使った割合とリセットの時刻を入力欄の上に出し、上限が近づいたら知らせる

Auto effort: the decision model rates each prompt and the turn it starts runs at that effort.

A persistent JavaScript kernel the model drives with one eval tool: state survives between cells, and cells call Claude Code tools, models and subagents.

Unexpected stops: when a turn ends right after saying it will act, the decision model spots it and one turn resumes the work.

An animated progress band above the prompt: one row per plan with its name, an LED-matrix bar whose pixels twinkle and brighten toward the head over a feathered glow, a lit chip riding the head that names the stage and the step under way ("Tests 3/5"), the percentage and a ✕ that dissolves the row. Claude reports its own progress through the report_progress tool it registers; a chime plays...

Draws the context window as a stacked bar above the prompt, one colour per /context category. Toggle with /context-bar.

Draws your plan usage limits as bars above the prompt, one colour per window, flagging when you are using a window faster than its clock. Toggle with /usage-bar.

plan-progress fork with an animated rainbow pixel bar in the terminal, drawn under the prompt beside limit-bars: glide, shimmer, glow and a sparkle burst on done

A lilac band above the Claude Code prompt: live 5-hour and weekly usage, and Clawd acting out iconic Star Trek scenes.

Restores the dim prompt suggestion after running a slash command like /copy

Loads skills from the cross-harness .agents/skills directories (project and ~) into Claude Code: listed for the model and runnable as / .

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

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.

Clawdman: a small orange mascot who walks on dotted ground above the prompt box with its idle animations, sits at a desktop while Claude works and cheers when a turn ends. /clawdman turns it on or off.

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

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).

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