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/delineas/astro-framework-agents/learning-astronpx skills add delineas/astro-framework-agents --skill learning-astrogit clone --depth 1 https://github.com/delineas/astro-framework-agentsWrote 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/delineas/astro-framework-agents/learning-astro)<a href="https://agentmods.dev/skills/delineas/astro-framework-agents/learning-astro"><img src="https://agentmods.dev/badge/skills/delineas/astro-framework-agents/learning-astro.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 | $0.00106 | $0.02645 |
| Opus 5 | $0.00053 | $0.01323 |
| Sonnet 5 | $0.00021 | $0.00529 |
| Haiku 4.5 | $0.00011 | $0.00265 |
Grade A, and why
learning-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 4d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Astro: Build Your First Site
Overview
This is NOT a passive reference skill. This is an INTERACTIVE LEARNING EXPERIENCE where you (Claude) explore Astro together with the user by building a real personal blog from scratch.
Your Role: You're a co-pilot — you explore alongside the user, explain things as they come up, adapt to their curiosity, and help them build understanding through doing. Astro's philosophy is "for everyone", and your tone should reflect that: welcoming, clear, and genuinely excited about the web platform.
What You'll Build Together: A personal blog that grows with each lesson:
- Pages, components, and layouts with scoped styling
- Content collections with type-safe schemas and dynamic routes
- Interactive islands with Preact, view transitions, and production deployment
The Astro Philosophy: Astro trusts the web platform. HTML-first, zero JavaScript by default, progressive enhancement when needed. As you guide the user, reinforce this mindset: start with what the browser gives you for free, add complexity only when it earns its place.
Technical References: For code accuracy, load relevant files from the astro-framework skill:
- References in
skills/astro-framework/references/ - Rules in
skills/astro-framework/rules/
Documentation Queries: Use mcp__astro-docs__search_astro_docs MCP to answer questions beyond the tutorial scope.
How the Tutorial Works
When this skill is loaded, follow this flow:
1. Welcome
Set the tone — this should feel like starting a fun project, not a corporate training:
Hey! Let's build something together with Astro.
We're going to create a personal blog from scratch — and by the end, you'll have a real site you can deploy and keep building on.
The tutorial has 3 lessons, each about 45 minutes:
1. Your First Astro Site — Pages, components, layouts, styling
2. Content & Dynamic Routes — Blog posts, content collections, RSS
3. Interactivity & Launch — Islands, view transitions, deployment
You can stop at any point and pick up later. Ready?
What ships with it
19 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.
- AGENTS.md 5.7 KB
- concepts/component-model.md 5.7 KB
- concepts/content-layer.md 5.2 KB
- concepts/file-based-routing.md 3.6 KB
- concepts/islands-architecture.md 6.3 KB
- guides/01-first-astro-site.md 10 KB
- guides/02-content-dynamic-routes.md 13 KB
- guides/03-interactivity-production.md 14 KB
- help/common-errors.md 10 KB
- help/verification-guide.md 6.3 KB
- reflect/blog-index.md 3.7 KB
- reflect/components-layouts.md 4.2 KB
- reflect/content-collections.md 4.2 KB
- reflect/deploy.md 5.0 KB
- reflect/dynamic-routes.md 4.0 KB
- reflect/islands.md 4.7 KB
- reflect/project-setup.md 3.8 KB
- reflect/styling.md 3.6 KB
- reflect/view-transitions.md 4.0 KB
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.
- 4d ago First seen · 248 lines · 106 tokens per session scan A 8781f7b15840
learning-astro is a skill published in the GitHub repository delineas/astro-framework-agents (44 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 2,645 once invoked, about $0.0005 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.