Prompt

Reads Claude's replies out loud on macOS with ElevenLabs (via OpenRouter) or the built-in say voice. /speak to control it.

The record of orchestrated work: runs of units and tasks, the subagents spawned for them, each gate's verdict and the findings reviewers report, summed up in the status line while there is something to say. It can follow a superpowers plan document as its input. Run /ledger.

Learns from your corrections: keeps each one for you to confirm at session start, recalls the lesson when it is relevant again, and turns a repeated correction into a rule CLAUDE.md loads in every session.

Explains in Korean the shell command a permission dialog asks about, with what it would actually delete or discard (adapted from blast-radius), and asks before a risky loss in auto mode

One officer and a traffic light above the prompt, nothing else — napping idle, alert waiting on you, working, done

Codex-style queued follow-up inputs: the queue key while a turn runs holds the prompt until the turn ends, one per turn; alt+↑ edits the last one; an interrupt puts them back in the composer

Desktop mod for people who run many sessions: a task brief with criteria and authority at the start, Claude works alone and calls you only for blockers, an acceptance screen and an HTML report at the end. A free mode for brainstorming and prototypes keeps the ideas and ends with a summary. The task folder keeps the ledger, so compaction loses nothing.

Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a JSON snapshot and a JSONL event log

A band above the Claude Code prompt: an animated mini Claude that acts out what Claude is doing, who is working (model, effort, plan) and live ctx / 5h / 7d gauges.

A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.

Suggests next steps after every prompt and keeps them in a to-do list by category, in a panel you can click (/todo) or drive with commands.

Live plan progress bars with stages, steps, step times and soft sounds for decision, error and done. Local fork of zycck/claude-mods plan-progress 0.3.0 (ea2c96b) that sends its rules with the first prompt instead of prompt.compose and sends an unexplained open bar back from turn.complete instead of classic.Stop, redraws the bars from the transcript after a rewind or resume, folds the terminal...

A briefing card above the prompt: the session's state and how long it has held, its mission, the open asks it is waiting on you for (kept until a quoted reply closes them), what is burning money, what it found since you last sent a prompt, what comes next, plan progress, and each agent with its last activity. /now-doing asks lists every open ask; /now-doing sync opens the full briefing in a...

Turns a session into an orchestrator that delegates work to haiku and sonnet subagents, keeps its own context small, sizes each task to about 150K tokens of subagent context, and lists the running and past agents in an expandable band (/orchestrator on|off|status)

Live countdown above the prompt until your session's prompt cache expires, with an optional keep-alive that keeps it warm while you're away

Keep a copy of every Claude Code session that the 30-day cleanup cannot delete, as JSONL and readable markdown, with message times in the transcript and /history to list and search old sessions.

Shows Hebrew in the prompt (live mirror above the box) and in sent messages right-to-left and right-aligned, keeping code and English left-to-right

A IA não lê mais os .env (vê só o nome das chaves e se estão vazias); o usuário ganha o link do arquivo na tela para preencher

Guarda todo arquivo que a IA cria ou edita, em qualquer conversa: /entregas lista com link, e um "cadê" já chega respondido

Hands-free voice mode for Claude Code on Apple Silicon Macs: talk any time, hear short spoken replies, interrupt or add to work mid-task, run slash commands, and message or stop subagents by voice. Speech runs locally with Whisper and Kokoro.

Reusable prompt fragments kept across sessions: /snip add|rm|list|show, and ;;name expands in prompts

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)

Keeps the prompt cache of an idle Claude Code session warm: just before the cache lapses it submits a short service prompt, so your next message reads the context from the cache instead of writing it again. Off by default; /keepwarm on|off|status. Needs function hooks (early access).

A life coach that lives in Claude Code: notices your work rhythm, nudges at natural pauses, keeps small commitments, and coaches with Claude. Global evidence library plus a China pack. All data stays on your machine.