Menu
Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Orchestrate complex, multi-step AI workflows with quality convergence loops, event-sourced state, and human-in-the-loop approval gates. Use when the user wants to babysit a task, orchestrate a workflow, run quality-gated development, resume a previous orchestration run, diagnose run health, plan without executing, set up a project or user profile for babysitter, or assimilate an external methodology. Also use when the user mentions "babysitter", "orchestrate", "babysit", "quality loop", or "convergence loop".
Help and documentation for babysitter commands, processes, skills, agents, and methodologies.
Plan a babysitter workflow without executing it. Focus on creating the best process possible.
Install or refresh a team-pinned babysitter runtime/content setup from lockfile.
Start a babysitter orchestration run. Use this command to start babysitting a complex workflow.
Analyze a completed or in-flight run and propose process improvements for future runs.
| name | babysitter:yolo |
| description | Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution. |
| argument-hint | Specific instructions for the run |
Identical to /babysitter:call but runs in non-interactive mode:
babysitter run:create \
--process-id <id> \
--entry <path>#<export> \
--inputs <inputs-file> \
--prompt "$PROMPT" \
--harness codex \
--session-id "${CODEX_THREAD_ID:-$CODEX_SESSION_ID}" \
--plugin-root "$CODEX_PLUGIN_ROOT" \
--json
babysitter run:iterate .a5c/runs/<runId> --json --iteration <n>
For breakpoint effects, immediately post approval:
echo '{"approved":true,"response":"Auto-approved (yolo mode)"}' > tasks/<effectId>/output.json
babysitter task:post .a5c/runs/<runId> <effectId> --status ok --value tasks/<effectId>/output.json --json
completionProof is emitted, return it wrapped in <promise>PROOF</promise>The ONLY difference is that breakpoints are auto-approved and no user questions are asked. The orchestration loop, effect handling, and result posting are identical.