markitdown

markitdown is a skill for Claude Code, Codex from ErickRamirezAU/claude-skills. It costs 141 tokens per session (1,395 once invoked), scanned A, original, MIT.

A workflow for converting files and other sources into clean Markdown using Microsoft's MarkItDown command-line tool. Markdown is plain text with simple formatting for headings, lists, and links.

In plain words
What is it for?
Use it to convert supported files to Markdown and, with explicit approval, correct formatting problems such as broken sentences, missing headings, or spelling artifacts.
Why use it?
It gives you a readable text version of formats such as PDFs, Word documents, spreadsheets, images, audio, HTML, CSV, JSON, XML, ZIP files, and YouTube URLs, while allowing extraction problems to be reviewed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to convert supported files to Markdown and, with explicit approval…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erickramirezau/claude-skills/markitdown
Install

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.

Any agent
npx skills add ErickRamirezAU/claude-skills --skill markitdown
Clone the repo
git clone --depth 1 https://github.com/ErickRamirezAU/claude-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for markitdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/erickramirezau/claude-skills/markitdown.svg)](https://agentmods.dev/skills/erickramirezau/claude-skills/markitdown)
Your own site
<a href="https://agentmods.dev/skills/erickramirezau/claude-skills/markitdown"><img src="https://agentmods.dev/badge/skills/erickramirezau/claude-skills/markitdown.svg" alt="Measured on agentmods" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.01395
Opus 5 $0.00071 $0.00698
Sonnet 5 $0.00028 $0.00279
Haiku 4.5 $0.00014 $0.00139

Measured 6d ago against content hash 3abb254cf690, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ensure_markitdown.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/markitdown/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

markitdown

Convert a source file to Markdown, save it next to the source, and — only with explicit approval — clean up formatting artifacts left over from the conversion.

This skill wraps markitdown, Microsoft's open-source CLI for converting files to Markdown — all credit for the actual conversion goes to that project. This skill only adds the install-and-fix-up workflow around it.

Step 1: Resolve the input

The input may arrive as an attached file, a bare filename, or a full path.

  • If it's a full path or attachment, use it directly.
  • If it's a bare filename, check the current directory first, then common locations like ~/Downloads and ~/Desktop. If you find more than one match or none, ask the user rather than guessing — picking the wrong file is worse than asking a quick question.

Step 2: Make sure markitdown is installed

Run scripts/ensure_markitdown.sh. It checks whether markitdown is on PATH, already installed at ~/.local/bin/markitdown, or importable as a Python module even without a console-script entrypoint (covers venvs, system package managers, and non-standard pip installs) — and only installs it if none of those find it. No need to ask before installing. This mirrors how it was set up the first time, so re-running it on a machine that already has markitdown is a fast no-op.

The install path is platform-aware:

  • macOS uses Homebrew ([email protected], pipx), the reliable standard there.
  • Linux (including WSL, which reports as Linux) prefers pipx/pip3/pip directly and never requires Homebrew, since most Linux users won't have it.
  • Native Windows (Git Bash/MSYS/Cygwin, not WSL) looks for python3, python, or the py launcher, uses pipx if present or pip install --user otherwise, and checks %APPDATA%\Python\PythonXY\Scripts for the installed executable — pip's Windows install location, which isn't ~/.local/bin.

If the script still fails after that, surface the error to the user rather than trying alternate install methods — the failure usually means something about the machine needs their attention first (e.g. no pip available at all).

Read the full file on GitHub · 122 lines

Files

What ships with it

2 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.

Changes

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.

  1. 6d ago First seen · 122 lines · 141 tokens per session scan A 3abb254cf690

Subscribe to this mod's changes

markitdown is a skill published in the GitHub repository ErickRamirezAU/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 1,395 once invoked, about $0.0007 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.