Prompt

/mejora y una frase: Claude te hace 3-5 preguntas, escribe un prompt con contexto (sin rol), lo puntúa y lo corrige hasta el 9/10, con bucle o sin bucle. Método de diariovida.com.

After every Edit, Write, NotebookEdit or sed -i, a docked pane shows that file's uncommitted hunk with [keep] and [revert] buttons; a press dismisses or runs git checkout with no model turn.

Run herdr software factories through this session: it ticks every run, runs a hidden patrol subagent as its manager, and draws a live console.

Claude Code mod that redraws the terminal transcript to look like the Code tab of the Claude desktop app: prompt bubbles, markdown tables, mermaid diagrams, folded tool calls, agent cards, plan card, GitHub/GitLab PR bar, Asana tasks, Slack DMs, diff, context, background tasks and Markdown preview panes

Untangles the interleaved work in a Claude Code session (prompts, mid-turn asides, subagents, loops) into colour-coded streams with a live navigator pane, a status bar of pills and per-stream focus.

Keeps a live local page for a long Claude Code task: what needs you, what was built, what was verified, and what was decided without you. Hooks record it without spending model tokens, the page follows light, dark or your system's setting, and when the task ends the same page is the report.

Session Panel: hides tool calls and shows a calm step checklist above the prompt, with a Hide/Show details button.

Caps parallel subagents and monitors; more need a stated reason and the user's approval

Answers Claude's numbered question rounds one by one in a panel, keeps confirmed answers across restarts, and sends them back as Q1: … lines

Passes prompts from a planning session to the session that does the work and its answers back, without copy and paste

Keeps subagents small: tells the main agent how to size and split work, asks a growing subagent to checkpoint, and refuses its tools past a hard limit so a fresh agent takes over

A persistent pane of actions Claude needs you to run: tick them off, pick an outcome, or reply, and Claude is told

[k-mods] Claude가 일하는 동안 입력창 위에 냥캣·Clawd·썬더 같은 픽셀 친구들이 지나가고, 턴마다 자라는 펫을 키워요. 엄선한 6가지 장면에 clawd-tales의 Clawd 이야기를 더한 한국어판. 원본: hoobnn/hoobnn-agent-mods의 spinner, plaxagoras/clawd-tales (둘 다 MIT)

Tracks what Claude Code costs — session, calendar-week and calendar-month totals with the month's pace and week-over-week change, a /costs pane with a spend calendar, the most expensive prompts and what filled the context, plus prompt-cache awareness: a cache warm/cold countdown, warnings before a prompt, model switch or large write re-caches the context, a per-category breakdown priced at...

Your Pokémon party journeys through a pixel world above the Claude Code prompt: it runs while Claude works, cheers when tests pass, faints when they fail, levels up and evolves.

/live: full-duplex voice (Kyutai streaming STT with semantic end of turn, or Silero and Whisper; Kokoro TTS) through a sidecar; /vibe: director mode that delegates all work to subagents; /livevibe: talk with a fast voice front that hands the work to Claude as director.

A pane of the project's dev servers: start, restart and watch them, and fill a crash's error into the prompt.

A GitHub pane in the side panel: the repo's open pull requests and issues; click one to open it in the browser, or fill /implement or /wayfinder with an issue. The issue a /wayfinder run works on is pinned at the top, with its next takeable ticket. A toast when your branch's pull request turns green or red, and a button that fills a fix on red.

One-click replies above the prompt: the options Claude just offered, Yes, Go with your recommendation, Continue, Pass, Fail and Skip when Claude asks for a verdict, and the next wayfinder ticket.

A pane in the side panel listing the next steps of your dev workflow, filled by /ask-sean; click a step to see its prompt.

Park an idea while Claude works, without interrupting it: /idea , or the shelf's own box. Ideas are kept per project across sessions, and Send puts one in the prompt box when you are ready. Starts off: /idea-shelf on turns it on

Hides secrets in tool results before Claude reads them: the secret values of every .env and .env.* from your session's folder up to the drive root, and anything that looks like a secret (KEY=VALUE under a secret name, passwords in URLs, private keys, JWTs, AWS keys, Kubernetes Secrets); tells Claude how to use them without printing them

A workspace pane for Claude Code: agents and worktrees, checkpoints, notes, changes and memory files in one tabbed pane

Windows only: a small floating strip over Windows Terminal that previews each [Image #N] you paste or drop, until you send