Claude Code UI and Transcript Mods

Trim long Bash output with Jev before the model sees it

Hide irrelevant tool result blocks and replace them with a summary stub

/linear: your Linear projects, milestones and issues in a pane beside the transcript

Play Subway Surfers (or watch any video) in a pane, rendered as glyphs with a foreground and a background color

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

Buttons above the prompt: retell recent turns in plain words, or open what a background check flagged that you might miss

Table foosball against a CPU opponent, in a pane: /foosball

A pane beside the transcript with the GitHub issues of the project the session works in

Reads Claude's replies and your prompts aloud on request, with the open-source Kokoro TTS model

Colors Claude's replies by meaning and makes the session easier to follow, every aid behind its own flag

Pages your phone (ntfy or Telegram) when the coding agent finishes a long turn or needs you, and lets you reply from the phone

Keeps AI-written code honest: flags flaky and bloated tests, trims wall-of-text replies, and makes you write the 'why' before a commit

Talk to your Claude Code sessions from your phone: voice notes out, voice replies back, over Telegram

One band above the prompt: quick replies, branch/PR/CI standing, decision cards, waiting-on-you items, standing-rule capture and a Hand off chip at…

Highlight CVE IDs in Claude's replies; hover one to see vuln.mlab.sh data

Status light for Render deploys in the status line, with a toast when one starts, goes live, fails or is canceled

Links ticket IDs, file paths, commit hashes and project terms in Claude's replies, with a hover card explaining each

A pane beside the transcript that fetches one Jira issue by key and lets you attach it to your next prompt

Stop being a meat proxy. Keeps Slack, GitHub and KakaoTalk requests in one inbox you open from any Claude Code session, where the session does the…

Claude の応答が流れてくる途中から Mermaid で図解する Mod。図にすべきか・どの図か・もう描いていいかの判断だけを Jev（TypeSafe AI の System One モデル）に確率で聞き、Mermaid のソースは決定的に組み立てる。

Cheaper Claude Code sessions: read and edit by stable line IDs, a model router that sends each task and agent to the cheapest model trusted with it…

Talk with Claude Code through the Avatar app: replies spoken as they are written by a face with lip sync, your voice into the prompt, and a pane with…

Listen to Claude's replies while the sentence being read is highlighted

Teamwork Chat inside Claude Code: unread badges, a conversations pane, replies, direct messages, images and suggested replies

Reads Claude's replies aloud as they stream, sentence by sentence, through VOICEVOX, Irodori-TTS or any command

Type in Chinese, talk to the model in English: translates prompts and replies with local Ollama, falling back to Google Translate

Masks sensitive names, orgs and secrets in the transcript for screen sharing; /mask toggles, click a mask to reveal

Teammate-style transcript rows for Specialists in Claude Code: channel wakes, the fallback wake, and Specialists MCP tool calls under native labels

Sound for Claude Code on Linux: mechanical key sounds as you type, and a chime when you send a prompt, when the reply lands and when a turn fails

Voice mode, tap to talk or hands-free: local Whisper transcribes you, Kokoro reads replies

Messages you on Slack when Claude has been waiting on you for a while (a finished turn, a permission prompt, a question); reply there and the session…

WebFetch を禁じ、代わりに ctxpack で Web ページをノイズ除去した Markdown として取得するツール (fetch_page) をモデルに提供するMod。ローカルLLMによる出典付きの関連段落抽出も選べる

Blocks AI sounding text in social media writing (X replies, X posts, LinkedIn posts) and injects the writing rules

One-click replies above the prompt: the options Claude just offered, Yes, Go with your recommendation, Continue, Pass, Fail and Skip when Claude asks…

RuFlo Graph Intelligence Engine — real-time relationship intelligence with complexity-aware execution