Commands

Clickable safety rules with presets: block rm -rf, force-push, destructive git, secret files, sudo, installs, network; lock Claude to the project folder or read-only; add your own block patterns.

Notification inbox + native OS notifications when a long turn ends, a subagent or background task finishes, or Claude is stuck waiting for your approval.

Before a vague prompt is sent, suggests a sharper rewrite; you choose: send improved, send yours, or edit the suggestion. Never rewrites silently.

A one-line launcher above the prompt: live context %, and one-click buttons for every claude-mods panel you have installed.

Every tool Claude can use (built-in and MCP) in plain language, how often each was used, and suggestions tailored to the project you are in.

Plan-limit bars with burn rate and time-to-empty, session cost, cache hit ratio and tokens-per-turn sparkline.

Claude desktop の Code タブに、CLI と同じステータスバー (statusline-command.sh の出力) を色つきで出す (issue 625)

Keeps a ledger of what Claude left running or lying around on your machine and servers

Live progress bars above the prompt for multi-step work: one row per plan, with stages, percent, waiting and failed colors, and sounds

Mask token-like strings in tool output before they reach the conversation

Cat mode: an ASCII cat above the prompt that reacts to what Claude is doing, plus status line and toasts.

A separate agent conversation in Claude Code's right-hand pane, forked from the current context.

A live typing speedometer above the prompt, a result card after each prompt (WPM, CPM, accuracy, personal bests) and a /typing stats pane

A Minecraft-inspired HUD for Claude Code: hearts for context, armor for safety nets, XP for verified work, and 60 advancements that persist across sessions

Sessions of this project, their worktrees and PRs, with check-ins, in a side pane.

Edit .env files in a pane inside Claude Code. Claude manages keys and asks you for values without ever seeing them.

Wakes an idle Claude Code session when its local file mailbox receives an addressed instruction, and records the session's replies to files the sender can read. Independent and experimental.

Liquid-filled rings above the Claude Code prompt for the 5-hour and 7-day limit windows, context fill and prompt-cache lifetime, a fighter jet that shows the model's effort, and a pane of recent turns, their cost, their share of the 5-hour window and what filled it.

Keeps a brief of the session above the prompt: what it is for and where it stands; /brief adds what was done and decided, what waits on you, and what comes next

Autonomous optimize-measure-keep/discard loop: skill, run/log/stats tools, and a live experiment dashboard

Autonomous experiment loop for Claude Code: run, measure, keep or discard. A port of pi-autoresearch.

claude review: the session's latest reply in a calm reading pane docked beside the conversation, with its plan, question and tasks one key away

Alt+E steps the effort level up and Alt+Shift+E down; the footer shows the model and level as they change

Replaces a secret with a format-preserving fake before the model reads it, and restores the real credential on the way into a tool call. The map survives a resume or a reload; set persist off to keep it in memory only.