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 dokmatiq/docgen-sdks --skill dokmatiq-docgengit clone --depth 1 https://github.com/dokmatiq/docgen-sdksWrote 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/dokmatiq/docgen-sdks/dokmatiq-docgen)<a href="https://agentmods.dev/skills/dokmatiq/docgen-sdks/dokmatiq-docgen"><img src="https://agentmods.dev/badge/skills/dokmatiq/docgen-sdks/dokmatiq-docgen/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/dokmatiq/docgen-sdks/dokmatiq-docgen"><img src="https://agentmods.dev/badge/skills/dokmatiq/docgen-sdks/dokmatiq-docgen.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 | $0.00308 | $0.02090 |
| Opus 5 | $0.00154 | $0.01045 |
| Sonnet 5 | $0.00062 | $0.00418 |
| Haiku 4.5 | $0.00031 | $0.00209 |
Grade A, and why
dokmatiq-docgen 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 10d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dokmatiq DocGen — Document Generation, Excel & Receipt Recognition
Generate professional PDF, DOCX, ODT documents and Excel spreadsheets from HTML/Markdown with templates, tables, QR codes, e-invoicing (ZUGFeRD/XRechnung), digital signatures, AI-powered receipt recognition, and more.
Prerequisites
This skill requires the Dokmatiq DocGen MCP server to be configured in the MCP client that loads the skill.
- Get an API key at https://developer.dokmatiq.com
- Install the MCP server:
python3.11 -m pip install --user dokmatiq-docgen-mcp
The MCP server requires Python 3.11 or newer. If the docgen-mcp command is installed into ~/.local/bin, make sure that directory is on PATH for the MCP client, or use the absolute command path in the client configuration.
- Make the API key available to the MCP server, either through the client config or the process environment:
export DOCGEN_API_KEY="dk_live_xxxxxxxxxxxxx"
- Restart or reload your MCP client so it picks up the configuration.
Client setup notes
- Plugin-based clients can auto-register the MCP server from the bundled
.mcp.json. - JSON MCP configs should use a literal API key in
envor rely on the process environment. Do not assume${DOCGEN_API_KEY}is expanded unless the client explicitly documents that behavior. - Hermes users should configure the server in
~/.hermes/config.yaml:
mcp_servers:
docgen:
command: "uvx"
args: ["dokmatiq-docgen-mcp"]
env:
DOCGEN_API_KEY: "dk_live_xxxxxxxxxxxxx"
- Claude Desktop, Cursor, Continue, Cline, and similar MCP clients can run the same server command (
docgen-mcporuvx dokmatiq-docgen-mcp) as long asDOCGEN_API_KEYis available to the server.
Capabilities
Document Generation
Simple conversion:
generate_pdf_from_html– Convert HTML to PDFgenerate_pdf_from_markdown– Convert Markdown to PDF
Advanced generation:
generate_document– Generate with template, field replacements, watermark, and output format selectioncompose_document– Compose a multi-part document from multiple sections (cover page, chapters, appendix)
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.
- 10d ago First seen · 168 lines · 308 tokens per session scan A 1cd3ea63b1cd
dokmatiq-docgen is a skill published in the GitHub repository dokmatiq/docgen-sdks (0 stars, last pushed 2mo ago), licensed MIT. It adds 308 tokens to every session and 2,090 once invoked, about $0.0015 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
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
analyze
Analyze a large file (CSV, Excel, PDF, JSON, code) and return a token-efficient summary. Instead of reading thousands of rows or pages, get schema + statistics + sample in under 500 tokens. Use when user mentions a file path, asks to analyze data, pastes many rows, or references a CSV/Excel/PDF/JSON file.
sap-docs-extract
Reads a SAP design document (Excel .xlsx, Word .docx, PDF) — or an existing work folder / a raw.txt file — and extracts structured information into separate text files by type: program summary, domains, data elements, tables, error messages, text elements, and process logic. From a document it creates a fresh work…
faostat-analytical-brief
Use when the user wants a short, FAOSTAT-style analytical brief — a multi-page PDF policy document in the FAOSTAT house visual style, with a HIGHLIGHTS box, global/regional/country sections, numbered figures with source lines, explanatory notes, and a data appendix. Use when the user asks for "an analytical brief on…
learn
Ingests an external data source into the Second Brain. Fetches content from Confluence, Google Docs, GitHub repositories, remote URLs, or any local file format supported by docling (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, Markdown, CSV, and more), converts non-markdown formats to markdown via docling, runs the…
liteparse
Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question about its contents, look up a figure, or extract data. Provides fast, local, model-free extraction via the lit CLI with…