Prompt

入力欄の上の帯で、作業に合わせて Clawd（二次創作版）が踊り、使用量も表示する

Highlights the Needs you section of a reply, with the hopping Claude from the Stream Deck beside it, and turns its decisions into buttons.

Araçları tek satıra katlar, mesajları seçilen renkle vurgular

Press both ⌥ keys to give Claude what you're looking at: an article, selection, YouTube transcript, post with its comments, table, PDF, email or Finder files, also saved to Obsidian Clippings (macOS)

A pomodoro timer on the prompt's hint line whose break lands while Claude works, with buttons beside it, a history and a report: /pomodoro start

Snap a frame from your iPhone camera above the prompt and send it to Claude with your next message

Per-turn effort routing with TypeSafe's Jev, applied per request at turn.step. Off until /jev on.

Shows prompt cache hit rate and TTL status in Claude Code

LongPi: turns Claude Code into your personal longevity coach.

Bar above the prompt: cache time left, hit rate, context weather, compact button and API cost per model

Verifies signatures on the instruction files Claude Code loads, meaning CLAUDE.md, skills, and agent definitions, before they reach model context. It re-checks a skill bundle before the Skill tool runs it. Sigstore keyless, offline verification against a pinned trust root, no telemetry.

Tiny disposable learning cards under Claude Code's spinner while it works. Categories are markdown files.

A rubber duck in your Claude Code session: a quiet second opinion on each turn, a guard for risky commands, reminders, and lessons about your codebase

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.

Live spell check for the Claude Code terminal: red underlines in the prompt box, suggestion band above it

A chibi pixel witch who wanders your consoles, follows you between them, and sometimes picks fights

Session panel: context and usage limits, model, mode, agents and notifications, beside the transcript

A dashboard of the session's agents as coloured cats: their tasks, skills and run time, their questions answered in place with a meow, and the skills each task uses

Session-scoped, encrypted, read-only secrets that Claude uses in commands as {{ck:NAME}} without ever seeing them

Answer Claude's questions and quote its paragraphs with a click: numbered questions with clickable options, a ❝ on every paragraph, and the full context sent along with your message.

The time next to each of your messages.

Tool summaries and turn-duration lines in faint italic, with the time each turn finished.

A bar under the prompt with compact, clear, effort, model and a color per folder, plus a side chat for quick questions that don't interrupt the task.

Logs every MCP tool call and flags likely MCP gaps: browser fallbacks, tool errors, and answers that say the MCP can't do something. /mcp-gaps opens a pane; /mcp-gaps report exports a paste-ready list.