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 skills add G1Joshi/Agent-Skills --skill astrogit clone --depth 1 https://github.com/G1Joshi/Agent-SkillsWrote 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/g1joshi/agent-skills/astro)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/astro"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/astro/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.
<a href="https://agentmods.dev/skills/g1joshi/agent-skills/astro"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/astro.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.00490 |
| Opus 5 | $0.00010 | $0.00245 |
| Sonnet 5 | $0.00004 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
astro 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 9d 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
Astro
Astro is a web framework popularized for "Islands Architecture". It ships zero JavaScript to the client by default, hydrating only the interactive parts. Astro 5 (2025) introduces Server Islands.
When to Use
- Content Sites: Blogs, Documentation, Marketing sites.
- Multi-Framework: Use React, Vue, and Svelte components on the same page.
- Performance: Hard to beat for static content.
Quick Start
---
// Server-side code (Frontmatter) runs at build/request time
const data = await fetch('https://api.myjson.com').then(r => r.json());
---
<html>
<body>
<h1>{data.title}</h1>
<!-- Client Directive: This React component hydrates on load -->
<MyReactComponent client:load />
<!-- This Svelte component hydrates only when visible -->
<MySvelteComponent client:visible />
</body>
</html>
Core Concepts
Islands Architecture
The page is static HTML. Interactive widgets are "islands" floating in it. They hydrate independently.
Server Islands (Astro 5)
Async islands. The page loads instantly (static), and a specific island (e.g., "User Profile") loads asynchronously from the server and fades in.
Content Collections
Type-safe way to manage Markdown/MDX content.
const blogCollection = defineCollection({
schema: z.object({ title: z.string(), date: z.date() }),
});
Best Practices (2025)
Do:
- Use Server Islands: For dynamic personalization (e.g., "Logged in as Jeevan") without forcing the whole page to be dynamic (SSR).
- Use
<Image />: Astro's optimized image component is essential for LCP. - Mix Frameworks: Don't be afraid to use React for a complex search bar and Svelte for a simple toggle on the same site.
Don't:
- Don't use for complex dashboards: While possible (Hybrid Rendering), Next.js or Remix are often better suited for highly dynamic, authenticated apps.
References
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.
- 9d ago First seen · 71 lines · 19 tokens per session scan A c65802913407
astro is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 490 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
ui-designer
Elite UI/UX Design Lead & Frontend Architect. Generates distinctive, non-templated interfaces with opinionated aesthetics, deliberate typography, and exact UX copy. Triggers on UI design, frontend styling, or layout creation.
html-css-responsive
Custom Instructions: HTML5 & CSS3 Responsive Design Expert.
component-design
Design reusable React components with compound patterns, controlled/uncontrolled hybrids, typed prop APIs, async state handling, and ARIA accessibility. Use when the user creates, refactors, or reviews React components, or mentions props, hooks, .tsx files, component APIs, or accessible UI patterns.
css-architecture
Structure CSS/Tailwind for maintainability — tokens, BEM naming, specificity control, responsive patterns.
accessibility-testing
Run automated WCAG audits, manual keyboard/screen reader testing, and CI a11y gates.
awesome-accessibility-audit
An accessibility audit for web interfaces and markup, based on WCAG rules for people using keyboards, screen readers, or other assistive technology. It reviews structure, labels, focus, contrast, motion, and dynamic content.