---
name: multi-agent-status
language: en
description: "Show every multi-agent task's ID, phase, branch, and status. Use when asked what is running, or for an overview of every task."
user-invocable: true
---

# multi-agent status  -  Task Status Dashboard

Show every active and completed task as a table.

## Steps

1. **Detect project**  -  Find the repo root from cwd (if none, look at all known repos):
   - `~/my-ui-components/.worktrees/`
   - `~/my-figma-app/.worktrees/`
   - `~/my-ios-app/.worktrees/`

2. **Scan worktrees**  -  Read the `agent-state.json` file in each worktree directory:
   ```bash
   find {repo}/.worktrees/ -name "agent-state.json" -maxdepth 2
   ```

3. **Parse state**  -  For each task:
   - `taskId`, `branch`, `currentPhase`, `status`, `startedAt`, `autopilot`

4. **Show as a table**:
   ```
   🤖 Multi-Agent Tasks

   | ID | Jira/Task | Branch | Phase | Status | Duration |
   |----|-----------|--------|-------|--------|----------|
   | #1 | PROJ-133139 | feature/PROJ-133139-... | 7/7 DONE | ✅ Complete | 12m |
   | #3 | PROJ-133408 | feature/PROJ-133408-... | 7/7 DONE | ✅ Complete | 8m |

   💡 log #1 | resume #N | kill #N
   ```

6. **What is waiting to be learned** (one line, only when non-zero):

   ```bash
   node "$HOME/.claude/scripts/learn-from-transcripts.mjs" --json 2>/dev/null
   node "$HOME/.claude/scripts/observations.mjs" scan --status open --json 2>/dev/null
   ```

   Report `N lesson(s) minable from transcripts  -  /multi-agent:refactor to review` and `N open pipeline observation(s)` when either count is above zero, and print nothing when both are zero. Neither runs a model and neither writes: the miner is dry-run by default. Zero candidates with a non-zero `toolResultsExamined` means nothing to find; zero of both means the read is broken, which is worth saying rather than reporting a clean queue.

5. **Short command suggestions**  -  Based on state:
   - If there is a paused task → suggest `resume #N`
   - If there is a done task → suggest `log #N`