← ClaudeAtlas

ccc-consolelisted

The Commander Console: one inline panel — agents, usage, safety, memory, history — plus a prompt bar that reaches this session. Publishing a snapshot is separate and consent-gated.
KevinZai/commander · ★ 5 · AI & Automation · score 73
Install: claude install-skill KevinZai/commander
# $ccc-console — the Commander Console **The Console lives in your chat. Publishing makes a snapshot page you can keep or share.** One panel instead of four separate decks: who's working, what it cost, what got blocked, what you've done over the last month, and a box you can type into that reaches *this* session. It reads only your own local telemetry under `~/.claude/commander/` — the same logs `$ccc-mission-control`, `$ccc-usage` and `$ccc-safety` already read, composed once by `lib/console-model.js`. The one exception is **Memory**, which reads your own claude-mem store at `~/.claude-mem/` if (and only if) you have one. > 🔒 **Opening is local.** The inline widget renders from local logs and nothing leaves the machine. **Publishing is a separate act** and always asks first — see below. ## How it routes On `$ccc-console` with no argument, open the widget on the **Overview** tab (below). Explicit sub-commands skip straight to their tab or action: | Argument | What happens | |---|---| | `overview` (default) | agents working, anything awaiting your approval, task counts | | `usage` | saved / spent / dispatches, cost by app | | `safety` | blocked, auto-fixed, approved, tool-failure hotspots | | `memory` | recent claude-mem observation titles + counts — **optional**, see below | | `history` | the last 30 days day by day: cost, dispatches, tasks, failures, top skills | | `launch` | one-click chips for the common Commander workflows | | `refresh` | re-read the logs and rende