What is markitdown-for-ai AGENTS.md?

Project-specific instructions for working on markitdown-for-ai, a Docker version of Microsoft's tool for converting documents such as PDFs and Word files to Markdown.

Choose conventional commit types, update the changelog, understand the project overview, and follow its documented examples and types.

It explains the repository's conventions so changes follow its commit and release process.

How OpenTechIL/markitdown-for-ai configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to OpenTechIL/markitdown-for-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OpenTechIL/markitdown-for-ai/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/OpenTechIL/markitdown-for-ai

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/opentechil/markitdown-for-ai/agents-md/github.svg)](https://agentmods.dev/instructions/opentechil/markitdown-for-ai/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/opentechil/markitdown-for-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/opentechil/markitdown-for-ai/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/opentechil/markitdown-for-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/opentechil/markitdown-for-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 732 This file is loaded in full into every session.

When invoked 732 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00732	$0.00732
Opus 5.5	$0.00293	$0.00293
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 2mo ago against content hash 487ed1b62225, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

markitdown-for-ai AGENTS.md 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 2mo 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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This document provides guidance for AI agents working on this project.

Project Overview

MarkItDown Docker image - A containerized version of Microsoft's markitdown library for converting documents (PDF, DOCX, PPTX, XLSX, HTML) to Markdown.

Conventional Commits

This project uses Conventional Commits format:

<type>(<scope>): <description>

[optional body]

[optional footer]

Types

Type	Description
`feat`	New feature
`fix`	Bug fix
`docs`	Documentation only
`style`	Code style (formatting, no logic change)
`refactor`	Code refactoring
`test`	Adding/updating tests
`chore`	Maintenance, deps, build changes

Examples

git commit -m "feat: add support for stdin input"
git commit -m "fix: resolve permission issue with non-root user"
git commit -m "docs: update README with new CLI examples"

Release Process

When committing changes, always:

Update CHANGELOG.md - Add entry under [Unreleased] section:
- Use appropriate type: Added, Changed, Deprecated, Removed, Fixed, Security
- Be descriptive but concise
Update version in CHANGELOG.md - When releasing:
- Move [Unreleased] changes to new [X.Y.Z] section with date
- Update version links at bottom
Update README.md - If changes affect:
- New features or commands
- New environment variables
- Build instructions
- Usage examples

Tag release - For new versions:

git tag -a v1.0.0 -m "Release v1.0.0"
git push --tags

Docker Image Publishing

The GitHub Actions workflow (.github/workflows/docker.yml) automatically:

Builds and pushes to GHCR on push to main
Creates multi-platform images (amd64, arm64)

No manual Docker push needed - CI/CD handles it.

Skill Distribution

The document-to-markdown skill lives in skills/document-to-markdown/SKILL.md. It is installed via:

Read the full file on GitHub · 96 lines

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.

2mo ago First seen · 96 lines · 732 tokens per session scan A 487ed1b62225

Subscribe to this mod's changes

markitdown-for-ai AGENTS.md is an instructions file published in the GitHub repository OpenTechIL/markitdown-for-ai (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 732 tokens to every session, about $0.0029 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 2026-08-31.

Claude Code Documents PDF agent-skills agentic claude-skills markdown markitdown

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

markitdown-for-ai: Instructions file for Codex