mdc-file-format

A guide to MDC files, a Markdown-based format used for topic-specific rules in Cursor projects. These files are stored in the .cursor/rules directory and include a description and file-matching pattern.

In plain words
What is it for?
Use it to create or update MDC files, define which files a rule matches, and document commands or conventions such as Bun testing.
Why use it?
It explains how to write rules that apply to selected files, making project instructions easier for coding tools to use.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/dotneet/aica/mdc-file-format
Clone the repo
git clone --depth 1 https://github.com/dotneet/aica

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00183
Opus 5 $0.00000 $0.00092
Sonnet 5 $0.00000 $0.00037
Haiku 4.5 $0.00000 $0.00018

Measured 2d ago against content hash 065870ae0cb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mdc-file-format 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 2d 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.

.cursor/rules/mdc-file-format.mdc · 31 lines

What it actually says

The main purpose of an MDC file is to provide context related to a specific topic.

  • the file extension for MDC files is .mdc.
  • MDC files are stored in the .cursor/rules directory.

mdc file format

An MDC file consists of a header section with two fields:

description: A short description of the file's purpose. globs: A file-matching pattern.

example of mdc file

---
description: Use Bun for testing
globs: *.test.ts
---

This project uses Bun for unit testing.  
To run tests from the command line, use `bun test` or `bun test [path/to/file.test.ts]`.

bun:test has almost jest compatible functions like this.
import { describe, test, expect, beforeEach, afterEach } from "bun:test";
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. 2d ago First seen · 31 lines · 183 tokens per session scan A 065870ae0cb4

Subscribe to this mod's changes

mdc-file-format is a cursor rule published in the GitHub repository dotneet/aica (16 stars, last pushed 10mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 183 tokens. 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.