agentleFS
Sign inStart free
dylanjbarthdylanjbarth/agent-skills/skills/babysit/SKILL.md

babysit

Skill1 starsChanged 4 months agoMITView on GitHub

Keep a user-scoped task under observation in one continuous agent turn, waiting for a requested interval and running a specified read-only check after each wake. Use for babysitting CI, deployments, long-running commands, pull-request checks, another agent session, or any task that needs periodic status checks until a clear terminal condition, without creating external automation.

44 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use oh-my-issues, what-the and 10 more.

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.
  • tuliosalustiano27Skill

    oh-my-issues

    Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that close clusters atomically. Use when an issue tracker has accumulated dozens of reports that share underlying defects, when asked to triage / consolidate / cluster / dedupe issues, when asked to build a plan series or roadmap from open issues, or when routing a new incoming bug into an existing plan.

    Also in 3 projects that use this

  • tuliosalustiano27Skill

    what-the

    What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.

    Also in 3 projects that use this

  • Tsumugii24Skill

    split-to-prs

    Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

    Also in 4 projects that use this

  • mukcoSkill

    principles

    General software engineering principles — DRY, SOLID, YAGNI, KISS, naming, code smells, and refactoring. Language-agnostic. Use alongside language-specific skills.

    Also in 5 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 3 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 8

    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
  1. Distinctive:

    Run a foreground monitoring loop only.

    line 9
  2. Distinctive:

    Run the check once immediately unless the user explicitly asks to wait before the first check.

    line 20
  3. Very specific:

    Use the agent platform's native wait mechanism, keeping the turn active.

    line 24
  4. Distinctive:

    After every completed interval:

    line 26
  5. Distinctive:

    Run the exact check.

    line 28
  6. Distinctive:

    Stop and report immediately on success, failure, cancellation, a defined timeout, or an actionable change.

    line 30
  7. Distinctive:

    Do not claim a build or session is complete from elapsed time alone.

    line 33
  8. Distinctive:

    Keep wake reports compact: elapsed time, check number, current state, and only meaningful changes.

    line 37
  9. Distinctive:

    If the platform wakes early because the user sends a message, handle that message before resuming.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 42 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

Babysit

Run a foreground monitoring loop only. Do not create a cron job, scheduled workflow, background daemon, or external automation.

Start

Establish these four facts before waiting:

  1. The check to run at each wake; prefer a narrow, read-only command or connector call.
  2. The requested interval.
  3. The terminal conditions, including failure or timeout.
  4. Any maximum elapsed time or number of checks. If omitted, continue until a terminal condition or user interruption.

Run the check once immediately unless the user explicitly asks to wait before the first check. Report the starting state and monitoring contract concisely.

Monitor

Use the agent platform's native wait mechanism, keeping the turn active. If an interval exceeds one wait's supported maximum, chain waits. Do not substitute a long shell sleep.

After every completed interval:

  1. Run the exact check.
  2. Compare with the preceding result.
  3. Stop and report immediately on success, failure, cancellation, a defined timeout, or an actionable change.
  4. Otherwise, wait for the next interval and repeat.

Do not claim a build or session is complete from elapsed time alone. Inspect the live state. For CI, distinguish pending, passed, failed, cancelled, and unavailable.

Efficient output

Keep wake reports compact: elapsed time, check number, current state, and only meaningful changes. Do not emit a message merely to say that nothing changed unless the user asks for heartbeats.

If the platform wakes early because the user sends a message, handle that message before resuming. If a tool or session expires, report the last observed state and provide the exact next check command or action.

Examples

  • "Use $babysit to check the PR's required CI checks every 10 minutes until they all pass or one fails; stop after 90 minutes."
  • "Use $babysit to inspect the other agent session every 15 minutes until it completes, stops, or needs my input."

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