How do I install the Babysitter:yolo skill?

Run npx skillmds add majiayu000/babysitter-yolo in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Babysitter:yolo skill do?

Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution. It is listed under AI & ML on SkillMD.

Is Babysitter:yolo safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Babysitter:yolo?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Babysitter:yolo free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Babysitter:yolo?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Babysitter:yolo by majiayu000 — Agent Skill

Name: Babysitter:yolo
Rating: 4.2 (5 reviews)
Author: majiayu000

File contents

babysitter:yolo

Identical to /babysitter:call but runs in non-interactive mode:

Skip the interview phase — parse intent directly from the user's prompt
Auto-approve all breakpoints — never pause for human approval
No user questions — proceed autonomously through the entire orchestration loop

Workflow

Parse the initial prompt to extract intent, scope, and requirements
Research the repo structure to understand the codebase
Search the process library for relevant specializations/methodologies
Create the process .js file and inputs
Create the run:

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

Iterate until completion — auto-resolve all breakpoints:

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

When completionProof is emitted, return it wrapped in <promise>PROOF</promise>

Key Difference from /babysitter:call

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.

Frequently asked questions