AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Status

skill-proptermalone-proptermaltwo-status · by PropterMalone

One-shot dashboard of live background work — tmux sessions, queued background jobs, scheduled triggers, /loop crons, long-running processes, and in-session background tasks. Cheap, non-interactive. Use when orienting mid-session, after a gap, or when the user asks "what's running".

No reviews yet
0 installs
34 views
0.0% view→install

Install

$ agentstack add skill-proptermalone-proptermaltwo-status

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-proptermalone-proptermaltwo-status)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Status? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Report on everything running in the background. Goal: one compact block the user can read in five seconds.

1. Collect in parallel

Fire all of these at once — do NOT serialize. Each is cheap and independent.

tmux sessions

tmux list-sessions 2>/dev/null

For any session whose name suggests long-running work (matches download|embed|run-|batch|job|etl|watch), capture the last 10 lines:

tmux capture-pane -pS -10 -t 

Background job queue (optional — only if you run one)

If you have a local job-queue tool, list its pending/running/recent items here. Example with a `` CLI:

# Example — adapt to your own queue tool, or delete this block if you have none.
cd  &&  queue list 2>&1 | head -30

Note anything queued, in-progress, or recently completed. Flag overdue items. (If your queue CLI resolves dependencies relative to cwd — e.g. tsx does — cd into its directory first; running it from an absolute path can fail silently.)

Scheduled triggers (remote agents)

Use RemoteTrigger tool with action: list. Report:

  • Active triggers with their next fire time
  • Most recent run result per trigger

In-session crons

Use CronList tool. These are /loop or one-shot schedules created this session.

Long-running processes

Bound elapsed time to 10 min – 24 h to catch active work without drowning in machine-lifetime daemons:

ps -eo pid,etimes,cmd --sort=-etimes 2>/dev/null | awk 'NR==1 || ($2 > 600 && $2  —   (repeat per live session)
- Queue: N queued, M running — next:    (only if you run a queue)
- Triggers: N active, next fire , last  
- In-session crons: 
- Processes:    — (only if unexplained or >1h old)
- Background tasks: 

Flags: 

If nothing's running anywhere, just say "Background: nothing active." and stop.

4. Notes

  • This skill is read-only. Never kill, restart, or modify anything. If the user wants to act on something surfaced here, they'll say so.
  • If a probe fails (queue CLI path moved, tmux not installed, etc.), note it silently and continue with the others. Don't block the report on any single probe.
  • For very long-running jobs (overnight batches, multi-day downloads), include a rough percent-done or elapsed-time estimate if the tmux capture makes it obvious.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.