agentleFS
Sign inStart free
DeepusleepyDeepusleepy/t3-tots/skills/t3-status/SKILL.md

t3-status

Skill110 starsChanged 18 days agoMITView on GitHub

Short live answer about T3 work or a named job. Use for "status", "what's going on in <X>", "anything running?", "is <X> done?", "recap/where is <thread> at". Not for "catch me up/brief me" (t3-project-report) or "what needs me" (t3-waiting).

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md).

    line 8
  2. Very specific:

    No target ("status", "what's up in T3"): run t3q.py overview on every computer.

    line 11
  3. Distinctive:

    Not T3 (a benchmark, build, other long job, process or PR): use the checks in t3-watch "Pick the check" once.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md). Steps that use the box, ListMachines, routines, cards or SendToUser are Grok Bot only; other agents follow t3-tots-rules "Grok Bot only". Read-only.

Pick the mode

  • No target ("status", "what's up in T3"): run t3q.py overview on every computer. T3_DAYS defaults to 7.
  • A T3 project: t3ctl threads --project '<P>' --main --limit 8. Then run t3ctl status --thread '<id>' --json for each thread that is running, waiting, asking or in error, plus the newest one. Add t3ctl limits for anything stopped on a usage limit.
  • A thread: find it as in t3-tots-rules "Finding a thread". For a recap, raise T3_LAST to 20 or 30 until the story is clear.
  • PRs linked to a T3 thread: t3ctl pr --thread '<t>' or t3ctl prs --project '<P>'. Use gh as the fallback.
  • Not T3 (a benchmark, build, other long job, process or PR): use the checks in t3-watch "Pick the check" once. Report progress markers, such as level or percent done, and the last activity time.
  • Unclear: ask one short question.

Reply

  • Overview: per computer and project, one line per thread with title, state, last activity, and where it stands in your words. Put "needs you" first. Add one line for the hidden agent-spawned count, and flag threads with the same title on two computers.
  • One target: 2 or 3 lines. Say whether it is running, the last thing that happened and when, and anything waiting on the user. A recap may use up to 6 lines: goal, done, state, next or blocked, waiting on the user.
  • Offer the full briefing only when a lot is going on.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free