Commands

Lets Jev, a System One model, pick Claude's effort level for each prompt

Play Under Management while Claude works on a long turn. After 20 s of work, press 1: the game opens in a 960 x 600 window of its own and pauses itself when Claude finishes.

Multi-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model-economics, and a registry-driven external-worker layer.

An animated effort bar for Claude Code: Clawd casts Avada Kedavra at six ranks, one per effort level from low to ultracode, with Voldemort looming behind.

Bullswarm as a Claude Mod: live subscription meters for every installed coding-agent CLI above the prompt, quota-aware routing of Claude's own subagents to whichever pool has surplus, a verdict note on every bullswarm command the model runs, a /bullswarm command, and $.bullswarm for other plugins.

Time left on the working turn, on the spinner line: from the task list's pace, else from how long your turns run. No model calls, no tokens. /eta turns it on or off.

A live forecast of the context window, in the band above the prompt. /token-weather turns it on or off.

A Claude Code pane of your assigned Linear tickets by status; click one to load it into the session, read its details, comment, or change its status and priority

A slot machine you spin while your agent works. Chips come only from the tokens it burns. No real money: satire.

A blackjack table in a side pane to play while Claude works

Loop Subway Surfers gameplay in a Claude side pane while Claude works.

/compact-jev: Jev-guided verbatim compaction for Claude Code, called through Vercel AI Gateway. Never replaces /compact or auto-compaction.

A pane with the tree of child chats spawned from this chat: what each is doing, which branch it sits on, and what is still not merged. Read-only, no model calls.

Keeps a per-turn tally of edits, runs, curls and destructive commands and shows it on the turn footer; any non-read-only Bash counts as a run, a claim (English or Japanese) with no run flags the spinner, a destructive Bash unfolds its tool group, and an edit-without-run turn suggests running the tests.

Button-first Pomodoro timer above the Claude Code prompt: one-click focus blocks, a live countdown band, break reminders and a config pane.

ASD-STE100 (Simplified Technical English) and 80% Karpathy Mode plugin, mod, and skill for Claude Code. Enforces clean, unambiguous technical explanations.

Colorful replies: themed Markdown plus inline tags the model can write, drawn with real Ink Text styling

A Winamp-style player for Claude Code: live spectrum visualizer, scrolling marquee, playlist of tool calls and transport controls.

Play snake while Claude works. Every tool call Claude makes drops food into the game; the game pauses when Claude is done.

What this session has cost so far, live above the prompt.

Live USD PnL for the top 5 memecoin positions in a Solana wallet, plus a live chart terminal for any token. Helius only.

The context window as one row above the prompt, drawn the way Claude Code draws its own meters: the context's cells, the percentage used, the tokens over the window, and the tokens left before auto-compact. /context-view hides and shows it.

A Claude Code mod for Eunuch Mode: while the skill is on, the palace adviser stands above the prompt in pixel art, posing for what the agent is doing; the spinner narrates each action in court language; and the status line reads "Court in session". Canned lines by default; opt-in generative mode (fresh lines from Sonnet) and treachery mode (he plots your downfall, cosmetically). /court toggles...

See every running Claude Code session and worktree at a glance: status, branch, uncommitted work, staleness