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 ariaxhan/kernel-claude --skill marketing-sitegit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWrote 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/ariaxhan/kernel-claude/marketing-site)<a href="https://agentmods.dev/skills/ariaxhan/kernel-claude/marketing-site"><img src="https://agentmods.dev/badge/skills/ariaxhan/kernel-claude/marketing-site/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/ariaxhan/kernel-claude/marketing-site"><img src="https://agentmods.dev/badge/skills/ariaxhan/kernel-claude/marketing-site.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 | $0.00067 | $0.01032 |
| Opus 5 | $0.00034 | $0.00516 |
| Sonnet 5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
marketing-site 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<skill_load>skills/frontend/SKILL.md</skill_load>
- Audience: who arrives, what they know, and what situation brought them here.
- Desired action: install, buy, book, join, contact, learn, or compare.
- Offer: what changes for the visitor, how it works, and why this option is different.
- Friction: objections, risks, missing information, switching cost, and alternatives.
- Proof: product behavior, demo, screenshots, founder expertise, customer evidence, data.
- Brand and constraints: voice, assets, references, legal/privacy needs, stack, deadline.
Do not force an interview when the brief answers these. Ask only for a missing choice that would materially change the page; otherwise make a reversible assumption and label it.
Then choose a page argument that fits the buying decision. A useful default is: problem or desire → promise → mechanism → proof → objections → action. It is a diagnostic spine, not a mandatory section order. A familiar plugin may need one sharp idea and a demo; an expensive service may need process, proof, risk reduction, and detail.
Give each section one job. Prefer one primary CTA; secondary actions are allowed when they serve a genuinely different visitor state. CTA copy should name the next step, not “Submit.”
What ships with it
2 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.
- 6d ago Changed · -18 tokens per session 3553cab4943e
- 10d ago First seen · 99 lines · 85 tokens per session scan A 224e55af3594
marketing-site is a skill published in the GitHub repository ariaxhan/kernel-claude (13 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,032 once invoked, about $0.0003 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
brain-compiler
Generate or refresh SAN using the canonical contract and Agent Brain tools.
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
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.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…