ghost-app-ui-dev-setup

ghost-app-ui-dev-setup is a skill for Claude Code from TryGhost/Ghost. It costs 35 tokens per session (1,294 once invoked), scanned A, original, MIT.

A setup procedure for preparing an empty folder for local Ghost app interface development. It installs the needed Shade skills and local documentation, connects the Ghost app software kit, and checks that the local Ghost site is available.

In plain words
What is it for?
Use it before building Ghost app screens locally, especially when starting from an empty folder and a Ghost source checkout.
Why use it?
It gives a new project the same visible setup an outside developer would use and stops when required checks fail.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

Good fit Use it before building Ghost app screens locally, especially when starting from an empty folder and a Ghost source checkout.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tryghost/ghost/ghost-app-ui-dev-setup
About the project

Ghost is a publishing platform for creating websites, blogs, memberships, subscriptions, and newsletters. Publishers and developers can use it through managed hosting or run it themselves, while contributors work on its monorepo, themes, and API.

TryGhost/Ghost · 55,632 stars · on GitHub · ghost.org

Install

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.

Any agent
npx skills add TryGhost/Ghost --skill ghost-app-ui-dev-setup
Clone the repo
git clone --depth 1 https://github.com/TryGhost/Ghost

Made for: Claude Code.

Wrote 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.

agentmods badge for ghost-app-ui-dev-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/tryghost/ghost/ghost-app-ui-dev-setup/github.svg)](https://agentmods.dev/skills/tryghost/ghost/ghost-app-ui-dev-setup)
Your own site
<a href="https://agentmods.dev/skills/tryghost/ghost/ghost-app-ui-dev-setup"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/ghost-app-ui-dev-setup/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.

agentmods 80×15 button for ghost-app-ui-dev-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/tryghost/ghost/ghost-app-ui-dev-setup"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/ghost-app-ui-dev-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01294
Opus 5.5 $0.00014 $0.00518
Sonnet 5.5 $0.00007 $0.00259
Haiku 4.5 $0.00003 $0.00129

Measured today against content hash 69a9f86391a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghost-app-ui-dev-setup scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Check `curl -s -o /dev/null -w '%{http_code}' http://localhost:2368/ghost/`
apps/shade/dev-skill/ghost-app-ui-dev-setup/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up a folder for Ghost app UI development

This prepares the current folder so a fresh chat can build a Ghost app the way an outside developer would: Shade's skills installed, Shade's docs served by the local Storybook, the app SDK packed from the Ghost checkout, and an AGENTS.md that reads like an ordinary app project's.

The build chat must see only what an outside developer sees. Keep the checkout path out of every file in the folder, except the deny rules in step 8.

Do the steps in order. Each ends on a check; when one fails, stop and tell the user. Commands and file contents are in reference.md.

1. Check the folder

  1. Confirm the current folder is empty. Hidden system files such as .DS_Store, or an empty .claude/, are fine. Anything else: stop and ask.
  2. Ask where the Ghost checkout is, suggesting ~/Code/Ghost. It's <checkout> below.
  3. Check <checkout>/apps/shade/package.json exists and the folder isn't inside <checkout>.

2. Ghost

  1. Check curl -s -o /dev/null -w '%{http_code}' http://localhost:2368/ghost/ prints 200.
  2. If not, offer to run pnpm dev:up in <checkout>, which runs Ghost in the background and prints its URL. Run it only on a yes, then check again.
  3. Remind the user that Settings → Labs → Private features → Apps must be on. You can't check it without logging in.

3. Storybook

Storybook serves Shade's docs as Markdown, which the skills read.

  1. Check curl -sf -o /dev/null http://localhost:6006/llms.txt succeeds. If so, go to step 4.
  2. Otherwise start it detached, as in Start Storybook, and poll llms.txt every few seconds for up to three minutes. If it never answers, show the end of its log and stop.
  3. Once it answers, record its process as in Start Storybook. Tell the user it keeps running after this chat, and how to stop it. Only give the stop command for a Storybook this setup started.

Read the full file on GitHub · 112 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. today First seen · 112 lines · 35 tokens per session scan A 69a9f86391a1

Subscribe to this mod's changes

ghost-app-ui-dev-setup is a skill published in the GitHub repository TryGhost/Ghost (55,632 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,294 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.