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 html-to-markdown-extracting-tablesgit 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/html-to-markdown-extracting-tables)<a href="https://agentmods.dev/skills/xberg-io/html-to-markdown/html-to-markdown-extracting-tables"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/html-to-markdown-extracting-tables/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/html-to-markdown-extracting-tables"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/html-to-markdown-extracting-tables.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 | $0.00036 | $0.00848 |
| Opus 5.5 | $0.00014 | $0.00339 |
| Sonnet 5.5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
html-to-markdown-extracting-tables 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extracting tables
Use this when the user wants tabular data out of HTML — pricing tables, data
grids, spec sheets. html-to-markdown parses <table> elements into two
surfaces: inline GFM Markdown tables in the content stream, and a
structured tables array when document structure extraction is enabled.
Two surfaces
# Inline GFM tables appear in the Markdown body
html-to-markdown input.html
# Structured table data appears under .tables in CLI JSON
html-to-markdown --json --include-structure input.html | jq '.tables'
- Markdown tables in
content—| col | col |blocks, good for LLM ingestion and human reading. - Structured
tablesarray — each entry has amarkdownfield (pre-rendered) and agridof structured cells (rows × cols). Use this when downstream code needs exact cell access.
Inline Markdown tables are rendered by default. Structured tables require
--include-structure in the CLI, include_document_structure=True in Python,
or includeDocumentStructure: true in Node.js.
Extraction-only
When you only care about tables (not the Markdown body):
html-to-markdown --json --include-structure --no-content input.html | jq '.tables'
Inspecting tables
# How many tables, and the row count of each
html-to-markdown --json --include-structure input.html \
| jq '.tables | to_entries | map({index: .key, rows: .value.grid.rows, cols: .value.grid.cols})'
# Just the rendered markdown of the first table
html-to-markdown --json --include-structure input.html | jq -r '.tables[0].markdown'
Line breaks in cells
By default <br> inside a cell is converted to a space. Keep hard breaks:
html-to-markdown input.html --br-in-tables
Programmatic access
from html_to_markdown import convert, ConversionOptions
html = "<table><tr><th>A</th><th>B</th></tr><tr><td>1</td><td>2</td></tr></table>"
# result.tables is only populated when include_document_structure=True
result = convert(html, ConversionOptions(include_document_structure=True))
for table in result.tables:
print(table.markdown) # rendered GFM markdown
print(table.grid.cells[0].content) # first cell (grid is a TableGrid)
What ships with it
1 file 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.
- 4d ago First seen · 101 lines · 36 tokens per session scan A c4f07815c7bd
html-to-markdown-extracting-tables is a skill published in the GitHub repository xberg-io/html-to-markdown (881 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 848 once invoked, about $0.0001 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 2026-10-15.
Other skills, from other repositories
xberg-picking-a-format
Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JSON, or DocTags. Maps consumer (LLM, parser, archive) to the right --format / --content-format pair.
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
docx
Read, create, or edit Microsoft Word .docx files — extract/summarize text and tables, generate reports/letters/memos with headings, tables, images, TOC and page numbers, do find-and-replace, or apply tracked changes (redlines) and comments. Use whenever the user has a .docx or wants a Word deliverable. Not for PDF…
Read, extract (text/tables), create, merge/split/rotate, watermark, encrypt, fill, and render-to-image .pdf files. Use whenever the user uploads a .pdf or asks to produce, edit, or pull data out of one.
pptx
Read, create, or edit PowerPoint .pptx decks — build slides from an outline, extract slide text/speaker notes, edit shapes/tables/charts, replace images, or export to PDF/images. Use whenever a .pptx (or .ppt) file is an input or output, or the user mentions a deck, slides, or a presentation.
xlsx
Read, create, or edit Excel spreadsheets (.xlsx/.xlsm) — sheet data, formulas, styles, charts, multi-sheet workbooks — and bulk .csv/.tsv tables; use whenever a spreadsheet is the input or the deliverable (extract/analyze data, add columns/formulas/formatting/charts, clean messy tables, build from scratch), but not…