Commands

Reusable prompts one command away: /snip review drops your saved review prompt into the prompt box, with {{selection}}, {{branch}}, {{date}} and {{args}} filled in.

Your standup, written for you: journals every Claude turn (prompt, files, commits) and turns yesterday and today into Yesterday / Today / Blockers with /standup.

A one-line TL;DR under every long answer, written by a small fast model, so you can skim a wall of text in two seconds.

A seatbelt for YOLO mode: blocks catastrophic shell commands (rm -rf ~, mkfs, dd to a disk, fork bombs) and asks before risky ones (force-push, reset --hard, DROP TABLE, curl | sh), even with permissions bypassed.

Explains a shell command in one plain-English line, with its risk, right where you approve it, so you know what you're saying yes to.

Keeps Claude's file edits inside the project: refuses writes outside it (symlinks resolved), never lets a tool touch .git internals, and asks before it changes lockfiles, CI workflows, migrations or secrets.

Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.

Stops data exfiltration and surprise network calls: checks every curl, wget, ssh, scp, git push and WebFetch against allow and deny lists, and asks before data goes to a host you haven't approved.

Keeps secrets out of Claude's context: API keys, tokens, private keys and passwords in tool output are replaced with [REDACTED:kind] before the model or the transcript ever sees them.

Stops Claude from installing hallucinated or typosquatted packages: every npm, pip, uv, poetry, cargo and gem install is checked against its registry first. Packages that don't exist are blocked; brand-new, barely used or lookalike packages ask you first.

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).

Lists your open Claude Code sessions in a side pane; click one to jump to its Ghostty tab (macOS)

ツール呼び出しのたびにClawdが1匹増え、持ち場で働く様子をペインに表示する作業状況モニター

Compacts an idle session just before its prompt cache goes cold, or keeps the cache warm while you're away, so your next prompt doesn't re-read the whole conversation uncached. Two chips under the prompt, /warm-compact and /keep-warm turn each on or off for a session.

Always-on status line and a pane for this session's Bash calls, background tasks and Codex/Pi/Devin/OpenCodeReview runs: elapsed time, output freshness, verdicts and errors.

Claude Code 의 슬래시 커맨드 설명, /config 항목, 일부 화면 문구를 한국어로 보여주는 번역 사전 mod (Korean UI translation dictionary mod)

A status band above the Claude Code prompt: 5-hour and 7-day plan limits, this month's API-equivalent cost with a daily activity grid, context use, session and last-turn cost, what a cache miss would cost, and a /compact button. Local only: no network requests.

Usage bar above the prompt (context, rate limits, cost, tokens) and a Workbranch pane: trial copies of your project you can save, bring into main or throw away. Italian and English.

Makes Claude explain its work in the fastest format to understand: STE-style text, diagrams, throwaway HTML pages or explainer videos, alone or combined, chosen by project and context.

A live map of your Claude Code session: a git-style flow chart, a live feed of every tool call, a drag-and-drop task board, async grill questions, agent chat, stats and recap, in a pane you can steer from.

Tells you when an atelier finishes: flux7-studio renders, as toasts and a line under the prompt

A machine face that watches tool calls and comments on them, with switchable avatars

Plays music from YouTube when asked in plain words, audio only through ffplay, with a small control pane

Live mesh7 decisions, pending approvals and emergency stops in a pane