All mods

Every file that changes becomes a crop: Claude's edits and yours grow a farm in its own pane, tests bring sun or storms, and passing turns fill the barn.

A vampire feeds on every tool call Claude finishes while the moon tracks how full the context window is. Between meals it stalks, swoops, and lies in wait. Dawn means it is time to compact.

A fox spirit that lives on your work: passing tests feed it, finished turns cheer it, it plays while you are quiet, and it grows up to nine tails.

A Claude samurai cuts down a Codex, Gemini, or ChatGPT foe for every tool call, and meditates, trains, and duels between them through four seasons.

See the decisions Claude made in each turn, why it made them, and steer future turns with keep and avoid rules.

While Claude works on your task, a sharp partner asks the questions that change the result. Answers reach Claude mid-turn. Brainstorm and side chat modes too.

Make Claude Code look the way you like: four themes (Retro CRT, Punk, Synthwave, Zen paper) switched with /theme, tidier tool calls, and optional one-line tool rows and replies centered at a reading width.

Notices when Claude drifts outside your request. Clear drift waits for your answer in a question dialog; milder drift is flagged above the prompt with a pull-back key.

Tanjiro, Nezuko, Zenitsu, and Inosuke take turns against demons up to Muzan as you and Claude work, and spar between strikes. The story continues every session.

Finds AI slop in Claude's changes (dashes, comment blocks, comments that repeat the code, tests that assert nothing, filler phrases) and tells Claude to remove it. Shows what was unslopped.

Picks Claude's effort level for each prompt with a System One decision model

Nyan Cat flies with its rainbow above the prompt while Claude works. /nyan changes its size or turns it off.

Live Vietnam stock-market heatmap and price board (SSI iBoard) in a Claude Code pane

Live process tree, RAM and CPU of your Claude Code session and everything it spawns

A small Claude Code mascot above the prompt, with usage, context, cache, directory and git status

Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context. Shadow mode by default: logs what it would do without changing anything.

Shows how the model decoded your request, next to your verbatim prompt. It never judges whether they agree — you do.

Masks secrets (API keys, tokens, passwords, private keys) in the transcript; hover a masked value to reveal it.

Live side pane listing the session's subagents: status, elapsed and working time, model, effort and estimated cost.

Side pane listing the tools used in the session (built-in, MCP, skill, agent, plugin, hook) with calls and token consumption.

Live Claude plan usage in Claude Code: 5-hour, 7-day and per-model weekly windows as slim meters, in the desktop app and the terminal

Resumes your Claude Code session automatically once the usage limit that stopped it resets

A Claude Code buddy: a pixel-art pet above your prompt that grows while you work and teaches you Claude Code