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 xberg-io/html-to-markdown --skill extracting-metadatagit clone --depth 1 https://github.com/xberg-io/html-to-markdownWrote 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/xberg-io/html-to-markdown/extracting-metadata)<a href="https://agentmods.dev/skills/xberg-io/html-to-markdown/extracting-metadata"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/extracting-metadata/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/xberg-io/html-to-markdown/extracting-metadata"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/extracting-metadata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01001 |
| Opus 5 | $0.00026 | $0.00500 |
| Sonnet 5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
extracting-metadata 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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extracting metadata
Use this when the user wants structured metadata out of HTML rather than (or in addition to) the Markdown body — page title, description, language, Open Graph tags, structured data, the heading outline, links, or image references.
Metadata lives in result.metadata and is surfaced on the CLI through
--json. On the CLI, metadata extraction is opt-in: pass
--extract-metadata alongside --json, otherwise result.metadata comes back
empty (document.title is null, headers/links/images/structured_data
are []). The library convert() call extracts metadata by default
(extract_metadata=True) — that default is a property of the API, not the CLI.
There are no per-field extraction flags: --extract-metadata populates all
sub-fields below at once.
Get all metadata
html-to-markdown --json --extract-metadata input.html | jq '.metadata'
# Extraction-only (skip the Markdown body)
html-to-markdown --json --extract-metadata --no-content input.html | jq '.metadata'
Metadata sub-fields
{
"metadata": {
"document": { "title": "...", "description": "...", "language": "en", "open_graph": {"title": "..."} },
"headers": [ { "level": 1, "text": "Main Heading" } ],
"links": [ { "href": "https://example.com", "link_type": "external" } ],
"images": [ { "src": "photo.jpg", "alt": "A photo", "image_type": "external" } ],
"structured_data": [ /* JSON-LD, Microdata, RDFa blocks */ ]
}
}
Metadata flag
There is one metadata flag: --extract-metadata. With --json set it populates
all sub-fields above (document, headers, links, images,
structured_data) under result.metadata — select what you need with jq.
| Flag | Effect |
|---|---|
--extract-metadata |
With --json: populate result.metadata. In plain-text mode (no --json): prepend title + meta tags as a YAML frontmatter block (----delimited) at the top of the Markdown output |
# Pull just the document-level metadata and the heading outline
html-to-markdown --json --extract-metadata --no-content input.html \
| jq '{title: .metadata.document.title, lang: .metadata.document.language, outline: [.metadata.headers[].text]}'
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.
- 9d ago First seen · 106 lines · 52 tokens per session scan A 0e44a544f2b7
extracting-metadata is a skill published in the GitHub repository xberg-io/html-to-markdown (864 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,001 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
document-chunker
Split documents into overlapping token chunks for RAG pipelines and LLM context windows. Zero dependencies.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.