Commands

Compacts an idle Claude Code session shortly before its 1-hour prompt cache expires, so coming back later re-sends a short summary instead of the whole conversation uncached.

A daily bodyweight rep goal inside Claude Code: log with /fit, quick-log band, long-turn nudges, streaks and a score grid, optional strict mode.

A pane showing each QRSPI task in thoughts/: which phase it is in, what blocks it, and the /qrspi:next command to run

Keeps a long-running agent's working notes through every compaction: briefs the summarizer, re-attaches the notes after the summary, and shows them in a panel you can steer.

Drive chottag (c-hottag) from Claude Code: switch the serving account, set the remote account, log accounts in, check limits and the install. On Claude Code 2.1.287+ a mod adds a status card, notices, /ct commands and a /login guard.

The classic mine-clearing puzzle in a Claude Code pane: click or use the keys to clear the board while Claude works. A timer, a best time, and a face that watches the board and glances over at Claude's work.

Explanations as visual pages in a pane beside the chat: diagrams drawn in place, the full page one click away. No model calls.

Holds a prompt back once your 5-hour or weekly usage is at or over a limit you set (90% by default); sending it again goes through. No tokens spent.

Asks before Claude edits a file another chat on this machine changed in the last 30 minutes. Each chat keeps its own small ledger; no model calls, no network.

A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, and which tools load on every request.

Tells you when a newer version of an installed claude-pro-kit mod is out, and /kit-update installs it. One small download per session, no tokens spent.

Desktop heads-up display for the Pro plan: exact 5h/7d usage gauges, context gauge, turn receipts, usage in the spinner and compact tool cards. No estimates, no tokens spent.

/receipt opens a pane with the exact tokens every turn of the session spent (uncached, cached, output, subagents) and the costliest turns. No tokens spent.

Moves tools you have not used lately behind ToolSearch, so their descriptions stop riding along on every request; core tools and anything you used in your last five sessions stay loaded.

Asks before a single turn uses more than +5 session points or 500,000 uncached input tokens, and stops it cleanly if you say so. Checks between requests, never mid-command.

Shows the images Claude's replies and tool results refer to, inline in the terminal transcript

Skins for Claude Code's transcript: themed tool rows, reply gutters and spinner words. /skin swaps them live.

Progress bars from your todo list at zero extra tokens, and a router where you pick the model and effort for quick, normal and hard prompts

Inspect the subagents reported by the session.

Play a local text animation whose frames are separated by a form feed.

Encode UTF-8 text or decode strict Base64.

Read authorship for the first 80 lines of a chosen tracked file.

Inspect local branches, upstreams, and dirty files.

Track API cache reads, writes, and uncached input by request.