メニュー
Help and documentation for babysitter commands, processes, skills, agents, and methodologies.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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".
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.
Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent design, acceptance test, component test, walking skeleton, in-memory fakes, component, contract test, adapter, fast tests, sub-second feedback. Language-agnostic (Go, Rust, Python, TypeScript, Java, C#).
| name | babysitter:help |
| description | Help and documentation for babysitter commands, processes, skills, agents, and methodologies. |
| argument-hint | [command|process|skill|agent|methodology] topic to get help on |
Help and documentation system for the babysitter Codex CLI plugin.
If no arguments provided, display this welcome:
Babysitter for Codex CLI — Orchestration Plugin
Primary Commands:
/babysitter:call Start an orchestration run (interactive)
/babysitter:resume Resume an existing run
/babysitter:yolo Start a run (non-interactive, no breakpoints)
/babysitter:plan Plan a workflow without executing
/babysitter:forever Start a never-ending periodic run
Secondary Commands:
/babysitter:doctor Diagnose run health (10 checks)
/babysitter:retrospect Analyze a run and improve future processes
/babysitter:model Set/view model routing policy
/babysitter:issue Start workflow from GitHub issue
/babysitter:team-install Install team-pinned setup from lockfile
/babysitter:assimilate Assimilate external methodology
/babysitter:user-install Set up babysitter for yourself
/babysitter:project-install Onboard a project
/babysitter:observe Launch observer dashboard
Type /babysitter:help <command> for detailed help on a specific command.
If an argument is provided:
.codex/skills/babysitter/<name>/SKILL.md and display its content.a5c/processes/<name>.js and describe it
upstream/babysitter/skills/babysit/processbabysitter skill:discover --plugin-root "$CODEX_PLUGIN_ROOT" --jsonUse the skill-loader module to resolve command names:
const { getSkillContent } = require('./.codex/skill-loader');
const content = getSkillContent(args);