lanes-status
Show the current state of all tmux lanes. Fast, visual, no ceremony.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Show the current state of all tmux lanes. Fast, visual, no ceremony.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Pause and reset. Gather what's scattered, commit what's ready, prepare for what's next.
Bootstrap a multi-agent project. Define the meta-process, resolve every open question, close the circle.
One agent flies high. Holds strategic context, names the unnamed, never descends into implementation.
Every session has a beginning, middle, and end. Design for session boundaries instead of being surprised by them.
Manage a multi-agent tmux workspace. Status, allocation, prompt drafting, cleanup.
Propose tmux lane allocations for pending work. Status view + assignment plan + sequencing logic.
| name | lanes-status |
| description | Show the current state of all tmux lanes. Fast, visual, no ceremony. |
Quick view of every pane in the current tmux window: what's running, what's idle, what's ready.
Run these three commands to gather the raw state:
# Inventory: index, size, process, PID
tmux list-panes -F '#{pane_index} #{pane_width}x#{pane_height} #{pane_current_command} #{pane_pid}'
# Titles
tmux list-panes -F '#{pane_index} #{pane_title}'
# Last few lines of each pane's output
for i in $(tmux list-panes -F '#{pane_index}'); do
echo "=== Pane $i ==="
tmux capture-pane -t "$i" -p | tail -8
done
From the captured output, determine state:
| Signal | State |
|---|---|
| Agent UI visible, recent output | Active — agent is working |
| Agent UI visible, waiting for input | Idle — session open, no activity |
| Shell prompt at the bottom | Shell — ready for new agent |
| Anything else | Unknown — investigate |
Present a single table showing the full workspace at a glance:
┌─────────────────┬────────┬──────────────────────┬──────────────────────────────────────────┐
│ Pane │ Size │ Title │ Status │
├─────────────────┼────────┼──────────────────────┼──────────────────────────────────────────┤
│ 0 (left) │ 162x82 │ "meta" │ Us — meta, active │
├─────────────────┼────────┼──────────────────────┼──────────────────────────────────────────┤
│ 1 (upper-right) │ 153x40 │ "Feature work" │ Stale — last session's agent, idle │
├─────────────────┼────────┼──────────────────────┼──────────────────────────────────────────┤
│ 2 (lower-right) │ 153x41 │ "Research" │ Shell — ready for new agent │
└─────────────────┴────────┴──────────────────────┴──────────────────────────────────────────┘
Include position hints (left, upper-right, etc.) when the layout is clear from pane sizes.
When the spatial layout matters, also render an ASCII view of the physical workspace:
┌─────────────────────────────┬─────────────────────────────┐
│ │ │
│ 0: META (us) │ 1: Feature work │
│ 162x82 — active │ 153x40 — stale/idle │
│ │ │
│ ├─────────────────────────────┤
│ │ │
│ │ 2: Research │
│ │ 153x41 — shell, ready │
│ │ │
└─────────────────────────────┴─────────────────────────────┘
This gives the operator an at-a-glance map of what's where.