agentleFS
Sign inStart free
aaroncohnaaroncohn/openspec-conductor-powerups/skills/pause/SKILL.md

pause

Skill1 starsChanged 9 days agoMITView on GitHub

Pause babysitter for now, so nothing new ships until `/babysitter:keep-going`. Run it in the Babysitter HQ workspace; anywhere else it changes nothing and says so.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use resume and init.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 7 projects that use this

  • MicrosoftSkill

    init

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Stop babysitter's own background work with TaskStop: its watcher, a send still waiting, a gh ...

    line 12

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

pause

The user wants babysitter to stop for now, with nothing new shipping until /babysitter:keep-going.

  1. Run python3 <this skill's dir>/../hq/state.py pause from this workspace's root. If it errors, this isn't Babysitter HQ: pass on what it said, change nothing, and stop. If it says already paused, say so and stop. Otherwise it lists the sessions to hold, one per line: name, then session.
  2. Stop babysitter's own background work with TaskStop: its watcher, a send still waiting, a gh ... --watch. Don't pkill: another repo's HQ runs the same script. Don't cancel a CI run or deploy already running; note it for step 4.

  3. Hold each listed session, plus any other you've been driving, with this message:

    Via Babysitter: the user has paused babysitting. Finish the step you're on, then stop. Until a "Via Babysitter: resumed" message, don't merge, archive or start the next step, unless the user tells you to here. Reply in one line with where you stopped.

    Locally: python3 <this skill's dir>/../hq/conductor-local.py send <session> <file> --now, because a working session may be about to merge. In the cloud: conductor message create, as in hq's cloud.md section 3; the listed ID is the workspace, so get its session with conductor workspace session <id> --json. Don't touch the Open Actions, Open Decisions or Open Tests workspaces.

  4. Post this, in plain words, with the first line exactly as written:
Babysitter is paused.
Held: <the workspaces>. <Any you couldn't reach, and what they may still do.>
Still finishing: <any merge, CI run or deploy already underway; leave this line out if there are none>
Open Actions, Decisions and Tests still work; I'll handle your answers when you keep going.
Run `/babysitter:keep-going` to pick up where this left off. If `◎ /goal active` still shows, run `/goal clear`.

Then follow hq's "Paused" rule: end every later turn with no text, unless the user asks you something.

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