What is Babysitter?

Babysitter enforces obedience to agentic workforces, enabling them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration. Define your workflow in code - Babysitter enforces every step, ensures quality gates pass before progression, requires human approval at breakpoints, and records every decision in an immutable journal. Your agents do exactly what the process permits, nothing more.

Prerequisites

• Node.js: Version 20.0.0+ (22.x LTS recommended)
• Claude Code: Latest version (docs)
• Git: For cloning (optional)

Installation

Babysitter supports multiple AI coding harnesses. Install the plugin for your harness of choice:

Claude Code (recommended)

Native marketplace install:

claude plugin marketplace add a5c-ai/babysitter
claude plugin install --scope user babysitter@a5c.ai

Restart Claude Code, then type /skills to verify "babysit" appears.

Plugin README

Codex CLI (Beta)

After cloning this repo, From within the Codex CLI:

codex
> /plugins

Navigate to the "babysitter" entry and select "Install".

Plugin README

Cursor IDE and CLI (Experimental)

Via the Cursor marketplace or npm:

npm install -g @a5c-ai/babysitter-cursor

Plugin README

Gemini CLI (Experimental)

npm install -g @a5c-ai/babysitter-gemini
babysitter-gemini install --global

Plugin README

GitHub Copilot (Experimental)

Via the GitHub Copilot CLI marketplace, or:

npm install -g @a5c-ai/babysitter-github

Plugin README

Pi (Experimental)

Native Pi plugin install:

pi install npm:@a5c-ai/babysitter-pi

Plugin README

Oh-My-Pi (Experimental)

Native omp plugin install:

omp plugin install @a5c-ai/babysitter-omp

Plugin README

OpenCode (Experimental)

npm install -g @a5c-ai/babysitter-opencode

The postinstall script copies the plugin to .opencode/plugins/babysitter/ automatically.

Plugin README

Internal Harness (No AI Coding Agent Required)

Babysitter ships with a built-in internal harness that runs processes programmatically without any external AI coding agent. This is useful for CI/CD pipelines, scripts, automated testing, and headless orchestration:

npm install -g @a5c-ai/babysitter-sdk

# Run a process definition using the internal harness
babysitter harness:call --harness internal --process .a5c/processes/my-process.js#process --workspace .

# Or run a free-form prompt
babysitter harness:call --harness internal --prompt "run lint and tests" --workspace .

The internal harness uses the SDK's built-in Pi execution engine directly. It supports all capabilities (Programmatic, SessionBinding, StopHook, HeadlessPrompt) and requires no external CLI.

During process execution, the internal harness can delegate tasks to any discovered installed harness via the invoker. A process running under --harness internal can spawn subagent tasks that execute through Claude Code, Codex, Gemini CLI, or any other harness found on the system -- the SDK discovers available harness CLIs at runtime and routes task execution accordingly. This means you can orchestrate a multi-agent workflow from a single headless entry point, with different tasks delegated to whichever harness is best suited for them.

Plugins

Babysitter has its own plugin system -- and it works differently from what you might expect. A babysitter plugin is not a code module with extension points. It's a set of natural language instructions (markdown files) or deterministic coded processes (JS files) that an AI agent reads and executes. The SDK stores, versions, and distributes the instructions. The AI agent is the runtime.

This means a plugin can do anything an AI agent can do: install npm packages, generate CI/CD pipelines, set up git hooks, create Terraform configs, modify your linter rules, copy babysitter processes into your project, and interview you about your preferences along the way.

The official marketplace includes plugins for security (gitleaks, ESLint security rules, audit processes), testing (Vitest/Playwright/pytest setup, coverage gates, TDD processes), deployment (Terraform, Helm, Dockerfiles, multi-environment pipelines), themes (sound effects, design systems, conversational personality), CI/CD (GitHub Actions workflows), and rate limiting (exponential backoff hooks).

To manage plugins, use the /babysitter:plugins command inside your harness (or babysitter harness:plugins from the CLI). The agent reads the plugin's install instructions, interviews you, analyzes your project, and executes the setup -- all within a babysitter orchestration run.

See the full Plugins documentation for details on how installs work, the marketplace format, creating your own plugins, and the migration system.

First Steps

After installation, set up your environment:

1. Configure Your Profile (One-Time)

/babysitter:user-install

This creates your personal profile with:

• Breakpoint preferences (how much oversight you want)
• Tool preferences and communication style
• Expertise areas for better process matching

2. Set Up Your Project

/babysitter:project-install

This analyzes your codebase and configures:

• Project-specific workflows
• Test frameworks and CI/CD integration
• Tech stack preferences

3. Verify Setup

/babysitter:doctor

Run diagnostics to confirm everything is working.

Quick Start

claude "/babysitter:call implement user authentication with TDD"

Or in natural language:

Use the babysitter skill to implement user authentication with TDD

Claude will create an orchestration run, execute tasks step-by-step, handle quality checks and approvals, and continue until completion.

Choose Your Mode

| Mode | Command | When to Use | |------|---------|-------------| | Interactive | /babysitter:call | Learning, critical workflows - pauses for approval | | Autonomous | /babysitter:yolo | Trusted tasks - full auto, no breakpoints | | Planning | /babysitter:plan | Review process before executing | | Continuous | /babysitter:forever | Monitoring, periodic tasks - runs indefinitely |

Utility Commands

| Command | Purpose | |---------|----------| | /babysitter:doctor | Diagnose run health and issues | | /babysitter:observe | Launch real-time monitoring dashboard | | /babysitter:resume | Continue an interrupted run | | /babysitter:help | Documentation and usage help |

Harness CLI Wrappers

Beyond the in-session skill commands (/babysitter:call, etc.), the Babysitter SDK provides harness:* CLI commands that let you create, run, and manage orchestration sessions from the terminal. These commands work with any installed harness.

Running Processes via a Harness

# Run a process interactively via Claude Code (pauses at breakpoints)
babysitter harness:call --harness claude-code --prompt "implement user authentication with TDD" --workspace .

# Run fully autonomous (no breakpoints)
babysitter harness:yolo --harness claude-code --prompt "add pagination to the API" --workspace .

# Plan only (stops after Phase 1)
babysitter harness:plan --harness claude-code --prompt "implement feature X"

# Run with the internal harness (no external AI agent needed)
babysitter harness:call --harness internal --prompt "run lint and tests" --workspace .

Managing Runs

# Resume an interrupted run
babysitter harness:resume --run-id <runId> --harness claude-code --workspace .

# Diagnose run health
babysitter harness:doctor --run-id <runId>

# Analyze past runs for insights
babysitter harness:retrospect --all --harness claude-code --workspace .

# Clean up old runs
babysitter harness:cleanup --keep-days 7 --harness claude-code --workspace .

Harness Discovery

# See which harness CLIs are installed on your system
babysitter harness:discover

# Install a harness CLI
babysitter harness:install claude-code

# Install a harness plugin
babysitter harness:install-plugin claude-code

Using `--harness inte