Commands

Barra lateral do Claude Code com modelo, contexto, custo, agentes, tarefas e um palco pixel art com personagens estilo SNES

Revisa lo que Claude escribe y lo que va a commitear, y se detiene si encuentra API keys, tokens, llaves privadas o contraseñas; /secretos muestra el historial. · Stops Claude before it writes or commits API keys, tokens, private keys or passwords.

A live pane listing every file Claude changed this session, with +/- line counts.

Tracks Claude's load across all your projects and charts it in a pane

Review a local diff in a pane with inline comments and suggestions, then send them to Claude

A quiet side pane: what this session is doing now, its plan, its agents as a tree, and every other Claude Code session with theirs

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and...

Null Radio — a cyber-neon internet radio pane for Claude Code: ten-channel synthwave + ambient dial, now-playing, VU, played through a local ffplay

A pane that shows the session's live status: doing now, decisions and surprises with one-click buttons, progress and the last update.

A side pane for the current session: prompt cache hot/cold, tool calls and errors, background commands with restart and stop, the approved plan, task list, subagents and swarm agents, and token usage for the main agent and subagents

A file browser pane: Enter puts @path in your prompt, l picks exact lines (@file#L12-30)

After a longer reply, offers to re-explain it in plain English, as a diagram, a web page or a video, sent now or edited first (after Karpathy's output-format tips).

Animated pane showing the orchestrator, its subagents, who is working and the messages between them

Pane with token usage per model as a GitHub-style activity graph, a pixel crab per model, cost share dials against the 5-hour or weekly limit, and account usage limits

Prompt-cache meter above the input box: hit %, read/wrote/new tokens, a TTL countdown and advice; cache-expiry toasts and context-window alerts. /cache opens a detail pane; /cache setup walks through every setting.

Shows your Claude plan's session and weekly limits above the prompt, gives Claude a plan_usage tool to check them without a model call, and can pause a long-running session before the session limit and continue after it resets.

A side pane listing every helper agent in the session: what it does, how long it has run, and when it finishes.

Records every file change Claude makes and plays the changes back frame by frame in a pane (/replay).

Shows how much of your Claude plan limits you have used, when they reset, and whether your current pace may reach them first.

Quanta Costa: your Claude subscription period, weekly limit with a pace forecast, session cost and plan value, as bars right above the Claude Code prompt.

Hand-drawn pixel-art cats and dogs wander above the prompt: they stroll, sit, nap, zoom, share hearts and chase each other. Choose how many, and cats, dogs or both.

A side pane (/side) where you talk directly to a subagent forked from the main conversation, while the main conversation keeps working.

A live stock pane (/ticker): a scrolling tape, prices, day change and an intraday sparkline for your watchlist, from Yahoo Finance.

Read, write and review markdown with Claude in a pane inside Claude Code: drafts stream in, comments stay on their words, and Claude suggests edits you accept or reject.