Mod plugins

Shows CPU, RAM, GPU and GPU RAM usage and totals in the status line or a live pane, on macOS, Windows and Linux

A pixel progress bar above the prompt with tasks done, percent and time left; a new colour each session.

Mod: session row above the prompt (cost, tokens, context, usage limits), a session panel, and a live progress bar for savvy-flow and any subagents.

Mod: a band above the prompt, a run pane and toasts for the request pipeline's lane, stage, MSPs, agents and verdicts.

Mod: hide tool output in the transcript, toggled with /no-command-output.

Mod: a pane listing the session's subagents with model, context, tokens, steps and time; /agents-inspector toggles it.

Mod: a dad joke beside the spinner while Claude works, a new one every minute; /dad-joke toggles it, /dad-joke-now tells one, /dad-joke-add-joke stores one, /dad-joke-more-jokes grows the collection.

Segmento da faixa acima do prompt: modelo em uso

Segmento da faixa acima do prompt: uso da sessão (5h) e semanal

Segmento da faixa acima do prompt: janela de contexto, com toast aos 80% e 90%

Band above the prompt: turn, output speed, turn and session cost, prompt cache countdown and context fill.

A row per subagent, workflow agent, Kiro run (kiro-cli chat) and background task: Pixel Clawd or Kiro's ghost in a costume (random by default), a submarine for background tasks, with running, finished and failed counts, time and a memory warning from 70% (/deck details adds cost, requests, tokens processed, memory and Kiro's credits), and a dithered progress band above the prompt while they run.

Guard for dangerous shell commands: blocks the catastrophic and stops the risky for a person to run or confirm.

Mod: IDE-style file tree (/filetree) that also marks the files Claude plans to change, is changing and has changed, opens their folders, shows a legend, and counts lines changed outside git. Fork of filetree.

Mod: /mods panel to turn installed plugins and mods on and off, browse your marketplaces and install from them.

Lists the small guesses Claude made without asking; mark each right or wrong, and a wrong one gets fixed on its own

Holds destructive commands (rm -r, force pushes, git resets and cleans, branch deletes, migrations, SQL drops) and shows what they would destroy

Mod: live panel of conductor agents with model, tokens, estimated cost and savings against all-Opus.

Live gauges above the prompt for context fill, the 5-hour and weekly plan limits (with pace and reset time), plus zero-token /clear vs /compact hints.

Shows the model and effort in use above the prompt, with a suggested model and effort for the task at hand.