agent-statuslisted

# /agent-status — Agent Status Dashboard > One screen. Health, queue, throughput, recent failures. No spelunking. ## Prerequisites Set these env vars (or pass via shell when invoking): | Var | Purpose | |---|---| | `AGENT_API_URL` | Base URL of the agent's HTTP API (e.g. `https://agent.example.com` or `http://localhost:7777`) | | `AGENT_API_TOKEN` | Bearer token for authenticated endpoints | The skill expects a task-queue-shaped agent that exposes endpoints roughly matching: - `GET /api/health` — health summary - `GET /api/tasks?status=running` — running tasks - `GET /api/tasks?status=queued` — queued tasks - `GET /api/tasks?status=failed&since=24h` — recent failures If your agent exposes different endpoints, adapt the curl invocations below. ## When invoked Pull a single dashboard frame answering: 1. **Health** — service up? DB reachable? Workers responsive? 2. **Active work** — what's running right now (count + brief task summaries) 3. **Queue** — how many queued, how long is the oldest 4. **Throughput** — tasks completed in the last hour / 24h 5. **Failures** — fail rate over last 24h, top 3 most recent failures 6. **Cost** — if the agent tracks per-task spend, sum last 24h ## Workflow ```bash # 1. Health curl -s -H "Authorization: Bearer $AGENT_API_TOKEN" "$AGENT_API_URL/api/health" # 2. Running tasks curl -s -H "Authorization: Bearer $AGENT_API_TOKEN" "$AGENT_API_URL/api/tasks?status=running" # 3. Queue depth + oldest curl -s -H "Authorization: Bearer $AGEN