DeepusleepyDeepusleepy/t3-tots/skills/t3-waiting/SKILL.md

t3-waiting

Skill110 starsChanged 18 days agoMITView on GitHub

T3 threads blocked on the user, each with a copy-ready reply, and showing or answering what one thread is asking. Use for "what's waiting", "inbox", "what needs me", "anything waiting on me", "what is <thread> asking".

In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- t3-checkupSkill
- t3-cleanupSkill
- t3-digestSkill
- t3-get-outputSkill
- t3-getting-startedSkill
- t3-handoffSkill
- t3-install-toolsSkill
- t3-new-threadSkill
- t3-phone-answersSkill
- t3-pm-threadSkill
- t3-project-reportSkill
- t3-project-trackerSkill
- t3-save-learningsSkill
- t3-statusSkill
- t3-syncSkill
- t3-templatesSkill
- t3-thread-actionsSkill
- t3-tots-rulesSkill
- t3-updateSkill
- t3-usageSkill
- t3-watchSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Follow the t3-tots-rules skill (skills/t3-tots-rules/SKILL.md).
line 8
Distinctive:
If it isn't answerable, tell the user to answer it in T3.
line 21

≈ “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". This skill is read-only, except for answering under t3-tots-rules "Decisions".

All threads

Run t3q.py waiting on every computer. T3_DAYS defaults to 14; T3_ALL=1 adds agent-spawned threads. A thread is waiting when it has a pending request or approval, a run in waiting, a held queue (a message waits for someone to resume or cancel it), or a last reply that ends in a question or hands a decision back. Running and settled threads are left out, and T3_DAYS counts from the last activity in the thread.
Run t3ctl limits on each computer and add threads stopped on a usage limit, with the reset time and whether auto-resume is set. A reset marked (passed) no longer blocks anything: list it once at the end as "can resume now" and offer to send a short continue, or to settle it if the work is done.
For each thread, give: computer, project, title, why it waits and since when (requests over 24 hours are stale), the question in one line, and a copy-ready reply in the user's voice in a code block. If only the user can decide, give 2 short options instead.
If all of an agent-spawned thread's requests are stale, label it "likely abandoned" and suggest dismissing it in T3. Group threads whose last reply is only a greeting or a "what can I help with" under one line, "idle chats", and offer to settle them.
End with the count, or one line if nothing waits.

One thread

Run t3ctl pending --thread '<t>' --json.
For a question with answerable: true, show it as a question card with the options exactly as listed. Answer with the user's pick as in t3-phone-answers "Answering", and confirm that it closed.
For an approval, show the prompt, the options and why it asks (approval.reason). Accept it only after the user's yes for that request (--user-approved), as t3-tots-rules "Decisions" says.
If it isn't answerable, tell the user to answer it in T3.

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