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.
git clone --depth 1 https://github.com/mfmezger/ai_agent_dotfilesWrote 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/commands/mfmezger/ai_agent_dotfiles/convert-to-markdown)<a href="https://agentmods.dev/commands/mfmezger/ai_agent_dotfiles/convert-to-markdown"><img src="https://agentmods.dev/badge/commands/mfmezger/ai_agent_dotfiles/convert-to-markdown.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00777 |
| Opus 5 | $0.00022 | $0.00388 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
convert-to-markdown 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document to Markdown Converter
Convert various document formats to Markdown using markitdown and pandoc.
Supported Formats
| Format | Extension | Notes |
|---|---|---|
| Text + OCR hybrid mode available | ||
| Word | .docx | Full support |
| PowerPoint | .pptx | Extracts text from slides |
| Excel | .xlsx | Converts tables |
| HTML | .html, .htm | Full support |
| EPUB | .epub | Via pandoc |
| Images | .jpg, .png, .gif, .webp | OCR extraction |
| Google Docs | URL | Public docs, exports as docx |
Usage
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py INPUT
Options
| Flag | Description |
|---|---|
-o, --output PATH |
Output path (default: input.md next to original) |
--mode auto|ocr|text |
Extraction mode (default: auto) |
--hybrid |
PDF only: run both text + OCR, merge results |
Examples
# Basic conversion (saves as document.md)
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py document.pdf
# Force OCR mode for scanned document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py scanned.pdf --mode ocr
# Hybrid extraction for PDFs with mixed content
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.pdf --hybrid
# Convert Word document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.docx
# Convert public Google Doc
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py "https://docs.google.com/document/d/DOCUMENT_ID/edit"
# Specify output location
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py slides.pptx -o notes.md
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.
- 8d ago First seen · 87 lines · 43 tokens per session scan A 116404a0cac8
convert-to-markdown is a command published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 777 once invoked, about $0.0002 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 commands, from other repositories
plannotator-annotate
Open interactive annotation UI for a markdown file.
audit-export
Exportar audit trail en JSON/CSV/PDF para auditorías externas. ISO 42001 & NIST AI RMF compliant.
confluence-publish
Publicar documentación del proyecto en Confluence. Convierte markdown a formato Confluence y crea/actualiza páginas en el espacio del proyecto.
biblio-search
Administra referencias bibliográficas con búsqueda por DOI, autor, año. Permite importar desde BibTeX, generar citas en múltiples formatos.
wtfp:export-latex
Export the manuscript and bibliography to portable LaTeX source with declared formatting.
brand-generate
Generate an on-brand document from a saved Brand Profile.