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 thomas-villani/all2md --skill all2mdgit clone --depth 1 https://github.com/thomas-villani/all2mdWrote 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/thomas-villani/all2md/all2md)<a href="https://agentmods.dev/skills/thomas-villani/all2md/all2md"><img src="https://agentmods.dev/badge/skills/thomas-villani/all2md/all2md/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/thomas-villani/all2md/all2md"><img src="https://agentmods.dev/badge/skills/thomas-villani/all2md/all2md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00181 | $0.01226 |
| Opus 5 | $0.00090 | $0.00613 |
| Sonnet 5 | $0.00036 | $0.00245 |
| Haiku 4.5 | $0.00018 | $0.00123 |
Grade A, and why
all2md 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
all2md
all2md converts between 40+ document formats and Markdown, from both the command line and a Python API. It reads PDF, DOCX, PPTX, XLSX, HTML, EML, EPUB, ODT/ODP/ODS, RTF, Jupyter notebooks, images, and 100+ source-code and config file types; renders Markdown back out to DOCX, PDF, PPTX, HTML, EPUB, LaTeX, RST, and more; and ships task commands for search, grep, diff, and static-site generation.
This file is the overview and index. Pick the task below and read the matching reference file for full CLI flags, Python API, and examples.
Choose a reference
| You want to… | Read | Command family |
|---|---|---|
| Read / extract text or tables from a document | references/read.md | all2md <file> |
| Convert a file from one format to another | references/convert.md | all2md <file> --output-format <fmt> |
| Generate a document or static site from Markdown | references/generate.md | all2md <md> --output-format <fmt>, generate-site, arxiv |
| Find a pattern inside documents (like grep) | references/grep.md | all2md grep |
| Ranked keyword/semantic search across a collection | references/search.md | all2md search |
| Compare two documents / see what changed | references/diff.md | all2md diff |
| Chunk a document for RAG/LLM pipelines (JSONL + provenance) | references/chunk.md | all2md chunk |
Core model
- Read:
to_markdown(path)/to_ast(path)auto-detect the input format and route to the right parser. - Write:
from_markdown(...)/from_ast(doc, fmt)render an AST to a target format. - CLI:
all2md <input> [--output-format FMT] [-o OUT]. Default output is Markdown to stdout. Use-for stdin. - Format-specific flags follow the pattern
--<format>-<option>for parsers (e.g.--pdf-pages) and--<format>-renderer-<option>for renderers (e.g.--html-renderer-no-standalone).
What ships with it
7 files 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.
- 9d ago First seen · 73 lines · 181 tokens per session scan A fcbf26c9dbe8
all2md is a skill published in the GitHub repository thomas-villani/all2md (27 stars, last pushed today), licensed MIT. It adds 181 tokens to every session and 1,226 once invoked, about $0.0009 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
deckprobe
Inspect PDF, Microsoft Office (docx/xlsx/pptx and legacy doc/xls/ppt), and Apple iWork (key/numbers/pages) files without opening or rendering them. Use for page and slide and sheet counts, title/author/created metadata, encryption and macro and digital-signature and JavaScript risk signals, sheet and table structure…
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
cli-anything-wps
A command-line tool that controls WPS Office on Windows, including Writer, Calc, and Impress. It can also build presentations from structured JSON data and export them as PowerPoint and PDF files.
doc-cleaner
Convert PDF, DOCX, XLSX, and text files to clean, structured Markdown. CJK-friendly, table-friendly, privacy-first.
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…