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-importsnpx skills add TryGhost/Ghost --skill shade-importsgit clone --depth 1 https://github.com/TryGhost/GhostWrote 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/tryghost/ghost/shade-imports)<a href="https://agentmods.dev/skills/tryghost/ghost/shade-imports"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/shade-imports.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.00401 |
| Opus 5 | $0.00020 | $0.00200 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
Shade imports 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 3d 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.
What it actually says
Shade imports
Always import Shade from its layer-specific subpath. Never from the root barrel @tryghost/shade.
Correct
import {Stack, Inline, Box, Grid, Container, Text} from '@tryghost/shade/primitives';
import {Button, Input, Dialog} from '@tryghost/shade/components';
import {PageHeader, KpiCard, Filters} from '@tryghost/shade/patterns';
import {ListPage} from '@tryghost/shade/page-templates';
import {cn, formatNumber} from '@tryghost/shade/utils';
import {ShadeApp} from '@tryghost/shade/app';
Note: ListPage is in @tryghost/shade/page-templates, not /patterns. Page templates are top-level page wrappers; patterns are the building blocks they compose.
Incorrect
// BAD — root barrel
import {Button, Stack} from '@tryghost/shade';
// BAD — deep path into source
import {Button} from '@tryghost/shade/src/components/ui/button';
Inside Shade itself
When editing files under apps/shade/src/**, use the @/ alias for cross-file imports:
import {cn} from '@/lib/utils';
import {inputSurface} from '@/components/ui/input-surface';
Why
Subpath imports make the layer (primitive/component/pattern) visible at the call site, which is the first piece of information a reader needs. The root barrel hides that and encourages cross-layer drift.
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.
- 3d ago First seen · 47 lines · 41 tokens per session scan A 39fc75d2b739
Shade imports is a skill published in the GitHub repository TryGhost/Ghost (55,095 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 401 once invoked, about $0.0002 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
add-form-manager
Introduce React Hook Form + Zod for form state, validation, and typed submission flows.
migrate-api-to-tanstack-query
Migrate the current REST API usage to TanStack Query with server-state caching, invalidation, and progressive rollout.
migrate-design-system-to-shadcn
Migrate the client UI layer from Chakra UI to shadcn/ui and fully remove Chakra dependencies.
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
seo-review
Perform a focused SEO audit on JavaScript concept pages to maximize search visibility, featured snippet optimization, and ranking potential.
flags
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.