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.
git clone --depth 1 https://github.com/iterationlayer/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/plugins/iterationlayer/skills/website-extraction)<a href="https://agentmods.dev/plugins/iterationlayer/skills/website-extraction"><img src="https://agentmods.dev/badge/plugins/iterationlayer/skills/website-extraction/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/plugins/iterationlayer/skills/website-extraction"><img src="https://agentmods.dev/badge/plugins/iterationlayer/skills/website-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
website-extraction 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 1mo 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
{
"name": "website-extraction",
"strict": false,
"description": "Extract structured data from public website pages using Iteration Layer",
"source": "./",
"skills": [
"./skills/convert-website-to-markdown-for-rag",
"./skills/extract-help-center-article-from-website",
"./skills/extract-job-listings-from-website",
"./skills/extract-news-article-metadata-from-website",
"./skills/extract-pricing-table-from-website",
"./skills/extract-product-data-from-website",
"./skills/extract-public-registry-page",
"./skills/extract-real-estate-listing-from-website",
"./skills/extract-restaurant-menu-from-website",
"./skills/extract-supplier-catalog-from-website",
"./skills/website-extraction-api"
]
}What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 288 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill convert-website-to-markdown-for-rag A 32 tokens
- Skill extract-help-center-article-from-website A 30 tokens
- Skill extract-job-listings-from-website A 28 tokens
- Skill extract-news-article-metadata-from-website A 31 tokens
- Skill extract-pricing-table-from-website A 26 tokens
- Skill extract-public-registry-page A 26 tokens
- Skill extract-supplier-catalog-from-website A 31 tokens
- Skill extract-restaurant-menu-from-website A 27 tokens
- Skill extract-real-estate-listing-from-website A 32 tokens
- Skill extract-product-data-from-website A 25 tokens
What ships with it
1 file beside marketplace.json#website-extraction 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.
- 1mo ago First seen · 19 lines scan A 39847beed49e
website-extraction is a plugin published in the GitHub repository iterationlayer/skills (4 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
all-skills
Every skill in the pack except task-router (Claude Code's native skill discovery does the routing): the fullstack profile plus AI agent docs and Docker.
fullstack
Frontend plus backend plus every review skill: architecture, UI, database, security, duplication audit, refactor planning, docs. task-router is excluded — Claude Code's native skill discovery does the routing.
backend
Minimal core plus backend API design, database schema and migrations, database review, security review, code review, repo audit, debugging, and test writing.
supabase
The backend profile plus Postgres/Supabase specifics: RLS, migration workflow, schema cache, auth integration.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.