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 RashadAnsari/myagents --skill markitdowngit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/rashadansari/myagents/markitdown)<a href="https://agentmods.dev/skills/rashadansari/myagents/markitdown"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/markitdown/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/rashadansari/myagents/markitdown"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/markitdown.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 | $0.00054 | $0.00455 |
| Opus 5.5 | $0.00022 | $0.00182 |
| Sonnet 5.5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
markitdown 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
Markitdown: Convert Anything to Markdown
The markitdown MCP server exposes a single tool that converts any supported resource to Markdown.
Tool
convert_to_markdown(uri: string) # on the markitdown MCP server
The uri parameter accepts:
| Scheme | Example | Use for |
|---|---|---|
file: |
file:///Users/you/report.pdf |
Local files on disk |
https: / http: |
https://example.com/page |
Web pages and remote documents |
data: |
data:text/html;base64,... |
Inline base64-encoded content |
Supported Formats
PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, ZIP archives, images (with EXIF metadata and OCR), audio (with speech transcription), EPubs, and YouTube URLs.
When to Use
- User says "convert this file to markdown", "read this PDF", "extract text from this Word doc"
- User pastes a file path and asks what is in it
- User wants to summarize or process a document before passing it to another tool
- User needs to index or search document content
How to Use
Local file:
convert_to_markdown(
uri="file:///absolute/path/to/file.pdf"
)
Always use an absolute path. Relative paths will fail.
Remote URL:
convert_to_markdown(
uri="https://example.com/document"
)
After Conversion
The tool returns the full Markdown content as a string. You can then:
- Write it to a
.mdfile in the project withWrite - Summarize or process it inline
- Pass it to another tool or agent
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 · 61 lines · 54 tokens per session scan A 681bff1e3a0e
markitdown is a skill published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 455 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
liteparse
Parse local document files into LLM-ready content on the daemon itself — PDFs → Markdown / structured JSON (with bounding boxes) / page screenshots via the bundled lit CLI. PDF works out of the box, offline, zero external deps (Tesseract + PDFium are bundled): digital PDFs use a near-instant native text path…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
ingest
Read web pages and search the web through the workspace Load lane. A query or URL returns document outlines with refs; pass refs back to read the original text of the sections you need, batch several refs in one call, and follow nextRef only while more evidence is needed. Use whenever the user gives a URL, asks you to…
work-markitdown
A document conversion tool that turns files such as Word documents, PDFs, PowerPoint presentations, spreadsheets, images, HTML, and CSV files into Markdown. Markdown is plain text with simple symbols for headings, lists, and other structure.
markitdown
A local document-conversion guide built around MarkItDown, a tool that turns files such as DOCX, PDF, PPTX, XLSX, images, HTML, and CSV into Markdown text.
Read, extract, merge, split, rotate, watermark, create, fill, encrypt, decrypt, and OCR PDF files. Use when the user mentions PDFs or needs any document workflow centered on .pdf files.