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/tryghost/ghost/shade-component-decisionnpx skills add TryGhost/Ghost --skill shade-component-decisiongit clone --depth 1 https://github.com/TryGhost/GhostWhat 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 | $0.00060 | $0.01236 |
| Opus 5 | $0.00030 | $0.00618 |
| Sonnet 5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
Shade component decision 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shade — pick the right layer (and decide whether to add to Shade at all)
Before adding anything to Shade, walk the decision flow and the promotion checklist. The default is keep code local first — premature design system additions lock in the wrong API.
The five layers
| Layer | Lives in | Examples |
|---|---|---|
| Token | theme-variables.css, tailwind.theme.css |
--background, --text-base, --radius-md |
| Primitive | src/components/primitives/ |
Stack, Inline, Box, Grid, Container, Text |
| Component | src/components/ui/ |
Button, Input, Dialog, Tabs, Card |
| Recipe | src/components/ui/<name>.ts (no JSX) |
inputSurface |
| Pattern | src/components/patterns/ |
PageHeader, KpiCard, Filters, GhAreaChart |
Plus one additional barrel:
page-templates/(@tryghost/shade/page-templates) — top-level page wrappers (ListPagetoday). Composes Patterns + Components + Primitives. If you're building a new shape that wraps a whole admin page, this is where it goes. Seeshade-page-templates.
Decision flow (top-to-bottom, stop at first match)
- Just a colour, size, radius, duration? → Token. Add to
theme-variables.css(semantic) ortailwind.theme.css(raw@theme). - Layout-only (spacing, alignment, structure)? → Primitive. Reuse an existing one; only add a new one if the structural shape is genuinely novel.
- Generic, accessible UI control with no Ghost-specific knowledge? → Component. Reuse first; only add if it doesn't exist and the promotion checklist below passes.
- The same chrome / focus / density rule shared across ≥ 2 components? → Recipe. A class-string function (no JSX, no React) next to the components in
src/components/ui/. - Knows about Ghost (KPIs, members, posts, newsletters, analytics)? → Pattern.
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 · 75 lines · 60 tokens per session scan A 71d91abdb6ab
Shade component decision is a skill published in the GitHub repository TryGhost/Ghost (55,095 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,236 once invoked, about $0.0003 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
seo-review
Perform a focused SEO audit on JavaScript concept pages to maximize search visibility, featured snippet optimization, and ranking potential.
fact-check
Verify technical accuracy of JavaScript concept pages by checking code examples, MDN/ECMAScript compliance, and external resources to prevent misinformation.
test-writer
Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
featurevisor
Author, query, and integrate Featurevisor — Git-based feature flags, A/B experiments, and remote config. Use whenever the user mentions Featurevisor, works in a project containing featurevisor.config.js, edits files under attributes/, segments/, features/, variables/, groups/, schemas/, targets/, sets/, or tests/…
javascriptcore-garbage-collector
JSC GC reference for Bun. Use for use-after-free, JS object leaks, "collected too early", or when touching WriteBarrier, visitChildren, visitAdditionalChildren, JSRef, JSC::Strong/Weak, hasPendingActivity, ensureStillAlive, addOpaqueRoot, reportExtraMemoryAllocated, IsoSubspace, HeapAnalyzer, finalize.