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 lossless-group/lossless-agent-skills --skill astro-knotsgit clone --depth 1 https://github.com/lossless-group/lossless-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/lossless-group/lossless-agent-skills/astro-knots)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/astro-knots"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/astro-knots/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/lossless-group/lossless-agent-skills/astro-knots"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/astro-knots.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 | $0.00123 | $0.03884 |
| Opus 5 | $0.00062 | $0.01942 |
| Sonnet 5 | $0.00025 | $0.00777 |
| Haiku 4.5 | $0.00012 | $0.00388 |
Grade A, and why
astro-knots 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 12d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astro Knots
A vision-mission masquerading as a stack: use the Internet as it was originally, idealistically intended.
Astro Knots is The Lossless Group's umbrella for a family of conventions across ~10+ Astro sites at various stages, built around Astro + Extended Markdown + SCM workflows + APIs. Think JAMstack with a steeper opinion gradient — and no one's heard of it yet.
Reference site: https://www.lossless.group/projects/gallery/astro-knots
When to use this skill
- Working in any Astro project under
lossless-monorepoor a sibling repo - Scaffolding a new Astro site (multiple new sites per quarter is normal)
- Choosing or adding dependencies — always check tech rules below before installing anything
- Building components, page layouts, content pipelines
- Integrating Lossless Flavored Markdown (LFM)
- User mentions "Astro Knots", "LFM", "extended markdown", "pseudomonorepo", or any of the ~10 site names
- Code review or refactor on an Astro Knots project
The vision (don't skip)
- Internet as originally intended. Documents, links, hypertext. Composable, not bundled. Readable URLs. Fast pages. Open formats.
- Build in public. Ship code and content together. Document thinking while shipping, not after.
- Generate meaningful content while shipping. Every project produces durable thought-artifacts (specs, blueprints, explorations). The work and the writing are the same activity.
- Forefront of Human + AI + Agent collaboration. Aspire to make a meaningful contribution to how humans and agents build things together. The
context-v/framework is one such contribution; LFM is another.
If a proposal contradicts these, push back before implementing.
The Tech Hierarchy
A strict preference order. Always reach for the lowest level that works.
- HTML & CSS — first choice. Semantic HTML, modern CSS (grid, flexbox, container queries,
@supports, native nesting). If HTML+CSS can do it, do not reach higher. - Vanilla JS — when interactivity is genuinely needed. Web standards (Fetch, IntersectionObserver, custom elements) before any helper.
- A small focused package — when vanilla JS would require reinventing something hard. Prefer single-purpose, low-dep, ideally tree-shakeable libraries.
- A framework — last resort, and only one of the approved few below.
What ships with it
7 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.
- 12d ago First seen · 206 lines · 123 tokens per session scan A a5a42d469d06
astro-knots is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 123 tokens to every session and 3,884 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…
tailwind-css
Master Tailwind CSS v4 with its CSS-first configuration paradigm. Use when writing utility classes, configuring design tokens via @theme, implementing dark mode, migrating from v3, or integrating with React/Vue/Svelte. Triggers on "Tailwind", "utility CSS", "Tailwind v4", "@theme", "dark mode classes", "responsive…
vercel-ai-sdk
Vercel AI SDK best practices and patterns. Use when building AI applications with React/Next.js and @ai-sdk/react, @ai-sdk/core, or @ai-sdk/ui. Covers useChat, streamText, generateObject, tool calling, and streaming architectures. SECURITY: Never pass raw user inputs to executable tools without strict Zod schema…
next-best-practices
Next.js and React performance optimization best practices - file conventions, RSC boundaries, data patterns, async APIs, Core Web Vitals, and bundle size. NOT for granular component caching strategies (use next-cache-components).
shadcn-ui
Use when adding, customizing, or structuring shadcn/ui components in a project. Also use when dealing with components.json, Tailwind configuration for shadcn, or component registries. Use when working with shadcn/ui, components.json, lucide-react, radix-ui, or Tailwind component registries.
next-upgrade
Upgrade Next.js to a specific target version using safe dependency bumps, codemods, and diff reviews. Use when you need to execute major version bumps, resolve breaking changes, "upgrading Next.js", "migrate to Next.js 15 or 16", or safely "run @next/codemod" against the repository before upgrading.