Ghost: Skill for Claude Code

.agents/skills/shade-input-surface-recipe/SKILL.md

Shade inputSurface recipe is a skill for Claude Code, Codex from TryGhost/Ghost. It costs 44 tokens per session (1,093 once invoked), scanned A, original, MIT.

A shared styling recipe for form controls in Shade, such as text fields, text areas, input groups, and select controls. It provides the common border, background, corner, focus, invalid, and disabled styling.

In plain words
What is it for?
Use it when editing form-control components or files in Shade, choosing the direct-focus mode for an input and the descendant-focus mode for a wrapper.
Why use it?
It prevents each form control from implementing slightly different visual and accessibility states.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is TryGhost/Ghost's own configuration. It tells Claude Code and Codex how to work on Ghost itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Ghost configures →

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

Reuse

Borrowing it

Nothing to install: this file belongs to TryGhost/Ghost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TryGhost/Ghost/main/.agents/skills/shade-input-surface-recipe/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TryGhost/Ghost

Made for: Claude Code, Codex.

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 Shade inputSurface recipe

README.md
[![agentmods](https://agentmods.dev/badge/skills/tryghost/ghost/shade-input-surface-recipe/github.svg)](https://agentmods.dev/skills/tryghost/ghost/shade-input-surface-recipe)
Your own site
<a href="https://agentmods.dev/skills/tryghost/ghost/shade-input-surface-recipe"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/shade-input-surface-recipe/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 Shade inputSurface recipe

Your own site · 80×15
<a href="https://agentmods.dev/skills/tryghost/ghost/shade-input-surface-recipe"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/shade-input-surface-recipe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.01093
Opus 5.5 $0.00018 $0.00437
Sonnet 5.5 $0.00009 $0.00219
Haiku 4.5 $0.00004 $0.00109

Measured 18d ago against content hash 3502ee56d06b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Shade inputSurface recipe 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 18d 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.

.agents/skills/shade-input-surface-recipe/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shade — inputSurface recipe

Form controls share one visual rule: border, background, radius, transition, focus ring, invalid state. That rule lives in inputSurface (apps/shade/src/components/ui/input-surface.ts) and is used by Input, Textarea, InputGroup, and the Select trigger. Don't duplicate the chrome — compose the recipe.

import {inputSurface, inputSurfaceClasses} from '@/components/ui/input-surface';
import {cn} from '@/lib/utils';

Two common modes

inputSurface('self') — directly on the focusable element

Use on <input>, <textarea>, or any element that itself receives focus.

<input
    className={cn(
        inputSurface('self'),
        'flex h-9 w-full px-3 py-1 text-control placeholder:text-muted-foreground',
        className
    )}
    {...props}
/>

Covers: base chrome + focus-visible: ring + aria-[invalid=true] styling + disabled: opacity.

inputSurface('within') — on a wrapper containing a focusable child

Use when the styled element is the wrapper (e.g. InputGroup) and focus state should react to any focusable descendant via :has().

<div className={cn(
    inputSurface('within'),
    'flex h-9 items-center gap-2 px-3',
    className
)}>
    <Icon />
    <input className="bg-transparent outline-hidden focus:outline-hidden" />
</div>

Covers: base chrome + has-[:focus-visible]: ring + has-[[aria-invalid=true]]: styling. (No disabled atom — wrappers don't get a disabled HTML attribute.)

Edge case — only one specific child triggers focus state

When 'within' is too broad (e.g. a wrapper with multiple focusables but only one should drive chrome), compose atoms manually so Tailwind's JIT can statically detect the class string:

import {inputSurfaceClasses} from '@/components/ui/input-surface';

<div className={cn(
    inputSurfaceClasses.base,
    inputSurfaceClasses.invalidWithin,
    // Literal class string — Tailwind needs to see it as text
    'has-[[data-slot=control]:focus-visible]:border-focus-ring',
    'has-[[data-slot=control]:focus-visible]:ring-2',
    'has-[[data-slot=control]:focus-visible]:ring-focus-ring/25'
)} />

Read the full file on GitHub · 113 lines

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. 18d ago Changed · +1 lines 3502ee56d06b
  2. 2mo ago First seen · 112 lines · 44 tokens per session scan A 583229b0482d

Subscribe to this mod's changes

Shade inputSurface recipe is a skill published in the GitHub repository TryGhost/Ghost (55,632 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,093 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 2026-08-30.

Related

Other skills, from other repositories

cms-metadata-tagger

Takes a finished piece of content and produces a complete, archive-ready metadata record — including descriptive tags, subject classifications, rights notes, and an archival summary — for entry into a content management or digital archive system.

ur-grue/autopunk-media-skills · 49 tokens

cms-metadata-writer

Writes structured metadata fields — title tag, meta description, tags, category, slug, and Open Graph text — for a CMS entry, optimized for search discoverability and social sharing.

ur-grue/autopunk-media-skills · 42 tokens

video-shot-demos

A workflow for creating animated HTML pages, one page per video shot, lesson segment, or narrated scene. It combines a shared player structure with different visual designs for each shot.

Unclecheng-li/AI_Animation · 166 tokens

hero-slider-settle

A render-quality slider rises past the target, corrects, then settles on 75%. Function: range control / preference set.

Unclecheng-li/AI_Animation · 0 tokens

hero-constellation

Nodes appear, links connect, then the graph gently rotates. Function: network / graph / system map (textless).

Unclecheng-li/AI_Animation · 0 tokens

exploring-autocapture-events

Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector uniqueness, query matching clicks ad-hoc, and create actions. Use when the user asks about autocapture data, wants to find what users are clicking…

PostHog/posthog · 127 tokens