markitdown-files

markitdown-files is a skill for Codex from pieable/dragon-ball-agent. It costs 101 tokens per session (732 once invoked), scanned A, original, MIT.

A file-conversion workflow that turns supported local PDFs, Office files, spreadsheets, HTML, images, and other materials into temporary Markdown for searching and analysis. It checks important text, numbers, and structure against the original file.

In plain words
What is it for?
Use it to extract, review, summarize, or analyze local files while keeping source locations and conversion limitations clear.
Why use it?
It makes content from non-Markdown files easier to inspect without changing the original. It also exposes extraction gaps instead of treating a conversion as a reliable copy of the source.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to extract, review, summarize, or analyze local files while keeping source locations and conversion limitations clear.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pieable/dragon-ball-agent/markitdown-files
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 pieable/dragon-ball-agent --skill markitdown-files
Clone the repo
git clone --depth 1 https://github.com/pieable/dragon-ball-agent

Made for: 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-files

README.md
[![agentmods](https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/markitdown-files/github.svg)](https://agentmods.dev/skills/pieable/dragon-ball-agent/markitdown-files)
Your own site
<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/markitdown-files"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/markitdown-files/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.

agentmods 80×15 button for markitdown-files

Your own site · 80×15
<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/markitdown-files"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/markitdown-files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 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 $0.00101 $0.00732
Opus 5.5 $0.00040 $0.00293
Sonnet 5.5 $0.00020 $0.00146
Haiku 4.5 $0.00010 $0.00073

Measured yesterday against content hash 3f8e24438fe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

markitdown-files 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 yesterday.

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-files/SKILL.md · 34 lines

What it actually says

MarkItDown file conversion

Use MarkItDown when the task needs the textual or structural content of a supported local file rather than its visual layout. Convert the original to a temporary Markdown file, inspect that Markdown, and keep the source file unchanged.

Resolve the executable from MARKITDOWN_EXE when explicitly configured, otherwise from PATH:

$converter = $env:MARKITDOWN_EXE
if (-not $converter) { $converter = (Get-Command markitdown -ErrorAction Stop).Source }
& $converter <input-file> -o <temporary-output.md>
  • Use an output location under the active workspace's work/ directory unless the user asks to retain the Markdown deliverable.
  • Prefer a format-specific document, PDF, or spreadsheet workflow when the task requires editing, page/layout verification, tracked changes, formulas, or a rendered visual result.
  • If conversion fails because an optional format dependency is missing, report the exact missing capability and install it only when the user authorizes that change.
  • Do not enable third-party MarkItDown plugins unless the user explicitly requests them.

部署材料

本 Skill 的公共主干与个人材料分开安装。涉及本地样例、档案或维护历史前,读取 本地依赖;缺失材料不等同于方法已执行。

核对转换结果能否支持当前分析

根据本次要回答的问题,先确定会影响结论的正文、数字、表格、图像或注释,在转换稿中定位,并与原件对应位置核对。检查相关章节是否取得,阅读顺序是否连贯,数字与单位、表头与数据、注释与所解释内容是否仍保持正确关系。转换进程成功与输出非空只说明生成了文件,后续分析所需内容的完整性和准确性由这些对应检查确认。

出现空页、大段缺失、乱码、异常数字、表格错列、跨页断句或注释归属不清时,回到原件确定问题来自原材料还是转换。按缺口选择格式工具:扫描页、图表及依赖空间位置的内容查看原页图像,表格计算核对原工作表的值、公式和单元格关系。OCR 或再次转换所得内容继续对照关键原件核验。已有正文可用时保留,只补取影响当前结论的缺失部分。

向后续分析交付原件入口及相应页、表或单元格定位,说明采用的提取稿、实际核对范围和仍未取得或无法确认的内容。存在关键缺口时先补取证据,无法取得则将对应主张保留为未知,并说明缺什么材料。转换稿用于查找和分析,争议数值与结构关系以原件核对结果为依据。

Files

What ships with it

3 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. yesterday First seen · 34 lines · 101 tokens per session scan A 3f8e24438fe1

Subscribe to this mod's changes

markitdown-files is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 732 once invoked, about $0.0004 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 2026-11-15.

Related

markitdown-files compared with skills from other repositories

markitdown-files next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
markitdown-filespieable/dragon-ball-agentSkill112d agoMITA101Codex
orbit-notionnexu-io/open-designSkill108ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill36k2d agoApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill50ktodayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill10ktodayApache-2.0A68Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A17Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A54Claude Code, Codex