Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add a5c-ai/babysitter --skill mcp-app-scaffoldinggit clone --depth 1 https://github.com/a5c-ai/babysitterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-scaffolding)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-scaffolding"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/mcp-app-scaffolding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-scaffolding"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/mcp-app-scaffolding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.02224 |
| Opus 5.5 | $0.00020 | $0.00890 |
| Sonnet 5.5 | $0.00010 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00222 |
Grade A, and why
mcp-app-scaffolding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-app-scaffolding
Scaffold MCP App projects from scratch with correct structure, dependencies, and framework-specific templates following the reference-code-first methodology.
Overview
MCP Apps are interactive UIs that render inline in MCP-enabled hosts (Claude Desktop, ChatGPT, VS Code, Goose, Postman). Every MCP App requires:
- A Tool (called by the LLM/host, returns data) registered via
registerAppTool - A Resource (serves bundled HTML UI) registered via
registerAppResource - The tool's
_meta.ui.resourceUrireferences the resource's URI
This skill handles the initial project scaffolding: cloning the SDK reference code, selecting a framework, generating the directory structure, and creating all entry points.
Capabilities
Reference Code Acquisition
- Clone SDK repository at exact published npm version
- Access framework templates from
examples/basic-server-{framework}/ - Access API reference source from
src/ - Access advanced patterns from
docs/patterns.md - Access basic-host reference for testing from
examples/basic-host/
Framework Selection Decision Tree
- React (first-class support): SDK-provided
useApphook,useHostStyles,useHostStyleVariables,useHostFonts - Vanilla JS: Manual App lifecycle, simplest setup, no framework overhead
- Vue / Svelte / Preact / Solid: Manual lifecycle management, follow team preference
Project Structure Generation
- Directory layout with
src/, build configs, entry points - Separate server and client source directories
- Proper
.gitignorefor build artifacts
Dependency Installation
- Runtime:
@modelcontextprotocol/ext-apps,@modelcontextprotocol/sdk,zod - Dev:
typescript,vite,vite-plugin-singlefile,tsx,concurrently - Framework-specific:
react,react-dom,@types/react,@types/react-dom(for React) - Always use
npm install-- never hardcode version numbers
Usage
Step 1: Clone Reference Code
# Clone SDK at the exact version published to npm
git clone --branch "v$(npm view @modelcontextprotocol/ext-apps version)" \
--depth 1 https://github.com/modelcontextprotocol/ext-apps.git /tmp/mcp-ext-apps
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 254 lines · 50 tokens per session scan A 8f9d733b5877
mcp-app-scaffolding is a skill published in the GitHub repository a5c-ai/babysitter (1,872 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,224 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
daw-cli
Instructs agents to control Stratawright DAW via the daw-cli command-line IPC interface. Covers session state, transport, track management, gain staging, VST3/AU plugin hosting, signal routing, clips, MIDI timeline editing, and non-visual DSP analysis & audio intelligence. Requires the DAW application to be running.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-define-goals
Define the product outcomes that should be achieved by solving the identified problem for the relevant users.