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 agentmods add skills/markus-global/markus/markitdownnpx skills add markus-global/markus --skill markitdowngit clone --depth 1 https://github.com/markus-global/markusWhat 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 | $0.00025 | $0.00497 |
| Opus 5 | $0.00013 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
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 2d 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 File Converter
You have access to the MarkItDown MCP tool (markitdown__convert_to_markdown) for converting files to Markdown.
When to use
Use this tool when:
- The user asks you to read, analyze, or summarize a document (PDF, Word, Excel, PowerPoint, etc.)
- You need to extract text content from an image (OCR)
- The user shares a file path and wants you to understand its contents
- You are working with a file format that your text tools cannot directly read
Note: For images attached directly in chat, the system automatically handles conversion when your model doesn't support vision. This skill is for converting files on disk that you encounter during tasks.
Supported formats
MarkItDown supports 29+ file formats including:
- Documents: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx/.xls)
- Images: JPEG, PNG, GIF, WebP (EXIF metadata + OCR)
- Web: HTML, XML
- Data: CSV, JSON
- Other: ZIP (iterates contents), EPUB, Outlook messages (.msg)
Usage
markitdown__convert_to_markdown({ uri: "file:///path/to/document.pdf" })
The tool accepts a file URI and returns the content converted to Markdown format.
Prerequisites
MarkItDown requires Python 3.10+ and the markitdown package:
pip install 'markitdown[all]'
Or install only specific format support:
pip install 'markitdown[pdf,docx,pptx]'
Best practices
- Check file existence first: Verify the file path is valid before attempting conversion.
- Large files: For very large documents, the converted markdown may be lengthy. Summarize key sections for the user rather than dumping everything.
- Image OCR quality: OCR results depend on image clarity. Mention if text extraction seems incomplete.
- Fallback: If conversion fails (e.g., markitdown not installed), inform the user and suggest installing with
pip install 'markitdown[all]'.
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.
- 2d ago First seen · 57 lines · 25 tokens per session scan A 72f3f67cd9eb
markitdown is a skill published in the GitHub repository markus-global/markus (157 stars, last pushed 6d ago), licensed Apache-2.0. It adds 25 tokens to every session and 497 once invoked, about $0.0001 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
dashclaw-ship
The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist. Lands feature branches on main (rebase, gate, merge, push so Vercel deploys), bumps the unified platform+SDK version, and realigns every description of the…
dashclaw-governance
Governance behavior for AI agents governed by DashClaw. Teaches the governance protocol: when to call guard (risk thresholds), how to interpret decisions (allow/warn/block/requireapproval), when to record actions, how to wait for approvals, and session lifecycle management. Loads org-specific policies and capabilities…
instrument-agent
Integrate DashClaw SDK into any agent using the 4-step governance loop.
troubleshoot
Debug DashClaw errors, signal issues, and misconfigurations.
compliance-drift-evals
Set up compliance exports, drift detection, evaluations, scoring, and learning analytics.
build-dashclaw
Contribute to the DashClaw codebase — architecture, scaffolding, tests, CI.