// Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until, etc.)
Pre-deploy gate that scans built JS chunks for forbidden substring markers (saga-era / obsolete code paths) listed in a project-local forbidden-markers.txt
Clean up .a5c/runs and .a5c/processes directories. Aggregates insights from completed/failed runs into docs/run-history-insights.md, then removes old run data and orphaned process files.
Plan a babysitter run. use this command to plan a complex workflow, without actually running it.
Orchestrate a babysitter run. use this command to start babysitting a complex workflow in a non-interactive mode, without any user interaction or breakpoints in the run.
Launch the babysitter observer dashboard. Installs and runs the real-time observer UI that watches babysitter runs, displaying task progress, journal events, and orchestration state in your browser.
help and documentation for babysitter command usage, processes, skills, agents, and methodologies. use this command to understand how to use babysitter effectively.
| name | babysit |
| description | Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until, etc.) |
| allowed-tools | Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSearch, Search, AskUserQuestion, TodoWrite, TodoRead, Skill, BashOutput, KillShell, MultiEdit, LS |
| version | 0.1.3 |
Follow the commands below exactly. but apply judgement and creativity to get the job done. no matter how small or simple the task may seem, you must use the babysitter SDK and run lifecycle to execute it. This is non-negotiable. If you are asked to do something that seems like it could be done with a simple tool call, you must still use the babysitter SDK to create a run, define tasks, execute them, and complete the run. This is how you will learn and demonstrate mastery of the babysitter system. Always follow the full process, even for trivial tasks.
Subagents that need a scratch checkout or working directory must create it under
/tmp/<descriptive-name>/, not under .a5c/runs/<runId>/work. Before returning
deliverables, validate that no run-dir worktree was left behind, for example:
find .a5c/runs -maxdepth 3 -name work -type d -print
That command should print nothing. If it prints a non-empty work directory, move or remove only the scratch data you created before returning.
Read the SDK version from versions.json to ensure version compatibility:
SDK_VERSION=$(node -e "try{console.log(JSON.parse(require('fs').readFileSync('${CLAUDE_PLUGIN_ROOT}/versions.json','utf8')).sdkVersion||'latest')}catch{console.log('latest')}")
npm i -g @a5c-ai/babysitter-sdk@$SDK_VERSION || npm i -g @a5c-ai/babysitter-sdk@latest
if command -v babysitter >/dev/null 2>&1 && babysitter --version >/dev/null 2>&1; then
CLI="babysitter"
else
CLI="npm exec --yes --package @a5c-ai/babysitter-sdk@$SDK_VERSION -- babysitter"
fi
If the pinned version fails to install (e.g. not yet published), the fallback installs latest.
If a stale or broken global shim fails with MODULE_NOT_FOUND, repair it with npm rm -g @a5c-ai/babysitter @a5c-ai/babysitter-sdk && npm i -g @a5c-ai/babysitter-sdk@$SDK_VERSION, then re-run babysitter --version.
Make sure jq is installed and available in the path. If not, install it.
Run the following command to get full instructions:
$CLI instructions:babysit-skill --harness claude-code --interactive
For non-interactive mode (running with -p flag or no AskUserQuestion tool):
$CLI instructions:babysit-skill --harness claude-code --no-interactive
Follow the instructions returned by the command above to orchestrate the run.