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 ianshk/astro-skills --skill astrogit clone --depth 1 https://github.com/ianshk/astro-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/ianshk/astro-skills/astro)<a href="https://agentmods.dev/skills/ianshk/astro-skills/astro"><img src="https://agentmods.dev/badge/skills/ianshk/astro-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/ianshk/astro-skills/astro"><img src="https://agentmods.dev/badge/skills/ianshk/astro-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 | $0.00072 | $0.01220 |
| Opus 5.5 | $0.00029 | $0.00488 |
| Sonnet 5.5 | $0.00014 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
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 2mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astro Skill
Reference for building static Astro sites (output: 'static'). Covers architecture decisions, content collections, SEO, image optimization, pagination, and deployment patterns.
Consult docs.astro.build and llms.txt for latest APIs when needed.
References
Read these files for detailed patterns and templates:
| Reference | What it covers |
|---|---|
content-collections.md |
Schemas (z.image, z.enum, reference()), querying, dynamic routes, entry.body |
image-optimizations.md |
<Image /> component, downscaling tip, SVG components, aspect ratios |
seo-checklist.md |
Head component, per-page checklist, structured data (JSON-LD), hreflang, content rules |
pagination.md |
paginate(), nested pagination, page prop |
Architecture Rules
1. Astro-first
.astrofiles for everything presentational — zero JS shipped to client.- Framework components (
.tsx,.svelte,.vue, etc.) only when interactivity is needed.
2. Minimal hydration
Use the lightest client:* directive that works:
| Directive | Use case |
|---|---|
client:load |
Critical above-the-fold interactivity |
client:idle |
Non-critical (modals, popovers) |
client:visible |
Below-the-fold widgets |
client:media |
Screen-size-specific UI (e.g. mobile sidebar toggle) |
client:only="<framework>" |
Browser-only APIs (e.g. localStorage, WebGL) |
3. Keep islands small
- Wrap only the interactive subtree in a framework component. Surrounding static markup stays in
.astro. - Pass data via props from the
.astroparent — never refetch inside islands.
4. Fonts via Fontsource
Always install fonts locally via Fontsource npm packages — never Google Fonts CDN links.
Example if using Inter
npm install @fontsource-variable/inter
What ships with it
4 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.
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.
- 2mo ago First seen · 129 lines · 72 tokens per session scan A 42d2dfcf7974
astro is a skill published in the GitHub repository ianshk/astro-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 1,220 once invoked, about $0.0003 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 2026-08-31.
astro compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| astroianshk/astro-skills | Skill | 4 | 4mo ago | MIT | A | 72 | Claude Code, Codex |
| openehr-assistantCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 182 | Claude Code |
| template-authoringCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 163 | Claude Code |
| archetype-authoringCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 128 | Claude Code |
| aql-authoringCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 102 | Claude Code |
| composition-builderCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 119 | Claude Code |
| demographic-modelingCadasto/openehr-assistant-plugin | Skill | 6 | 1mo ago | MIT | A | 126 | Claude Code |