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 agentmods add skills/mdcms-ai/mdcms/mdcms-studio-embednpx skills add mdcms-ai/mdcms --skill mdcms-studio-embedgit clone --depth 1 https://github.com/mdcms-ai/mdcmsWhat 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 | $0.00114 | $0.01777 |
| Opus 5 | $0.00057 | $0.00889 |
| Sonnet 5 | $0.00023 | $0.00355 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
mdcms-studio-embed 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDCMS Studio Embed
Mount the MDCMS Studio UI inside the user's own host app so editors work alongside product code. The canonical reference is apps/studio-example in the MDCMS repo — use it as the copy-from template for route structure, config preparation, and client bootstrap.
When to use this skill
The user wants a Studio UI under their own domain (e.g. app.example.com/admin/...) instead of running Studio standalone. If they only need the API and use Studio at the server's own /admin/studio route, skip.
Prerequisites
- A reachable MDCMS server and a working
mdcms.config.ts(runmdcms-brownfield-initormdcms-greenfield-initfirst). - A React app, ideally Next.js App Router. Other frameworks work but the reference implementation is Next.
- Ability to set server-side env vars on the MDCMS backend (for
MDCMS_STUDIO_ALLOWED_ORIGINS).
Steps
1. Install the Studio package in the host app
npm install @mdcms/studio
# or: bun add @mdcms/studio
2. Add a catch-all route
Studio is a single page app embedded at a catch-all route. The reference uses /admin/[[...path]] so every Studio route is served from one Next page. Copy the pattern from apps/studio-example/app/admin/[[...path]] in the MDCMS repo:
app/
admin/
[[...path]]/
page.tsx # server component that prepares Studio config
layout.tsx # minimal layout (Studio brings its own chrome)
admin-studio-client.tsx # client wrapper that mounts <Studio />
studio-config.ts # prepareStudioConfig + client-serialized subset
The server component calls prepareStudioConfig from @mdcms/studio/runtime against the full mdcms.config.ts, extracts a client-safe subset (component metadata, schema hash, route metadata), and passes it to the client wrapper.
3. Wire the prepared config to <Studio />
The client wrapper uses the <Studio /> component and the prepared config:
"use client";
import { Studio } from "@mdcms/studio";
import type { MdcmsConfig } from "@mdcms/studio";
export function AdminStudioClient({ config }: { config: MdcmsConfig }) {
return <Studio config={config} />;
}
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.
- 2d ago First seen · 131 lines · 114 tokens per session scan A 6bdaa93380dd
mdcms-studio-embed is a skill published in the GitHub repository mdcms-ai/mdcms (22 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 1,777 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
Shade imports
Import Shade from layer-specific subpaths (primitives, components, patterns, page-templates, utils), never the root barrel. Trigger when editing TSX/TS in Shade-consuming apps.
intlayer-next-js
Integrates Intlayer internationalization with Next.js App Router and Pages Router. Use when the user asks to "setup Next.js i18n", use "useIntlayer" in Server Components, or handle client-side translations in Next.js.
intlayer-react
Integrates Intlayer internationalization with React component. Use when the user asks to "setup React i18n", create a new translated component, use the "useIntlayer" hook, or configure providers.
react-effect-decision
Combine React's official "You Might Not Need an Effect" guidance with this project's stricter no direct useEffect stance. Use when writing, reviewing, or refactoring React components that might reach for useEffect, derived state, event relays, reset logic, subscriptions, or client fetching.
dev
Full-stack Convex development guidelines covering React, Vite, TypeScript, mutations, auth, design system, and documentation practices. Use when building features, writing Convex functions, or making code changes in this project.
Shade ShadCN install
Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.