Cursor often forgets .mdc instructions

Support Bug Reports
,
3

Hey, this is a known limitation. Rules in .mdc files are loaded into the model context, but LLMs can’t guarantee 100% compliance. They work probabilistically, so instructions like “always use PowerShell” or “always write comments in English” will be followed most of the time, but not always.

A few things that can help improve rule compliance:

  1. Keep rules short and direct. The shorter and more specific the instruction, the more likely the model is to follow it. Long rule files often get “diluted” in context.
  2. Use strong wording in the rule. Phrases like ALWAYS, NEVER, CRITICAL at the start of the rule help.
  3. Make sure alwaysApply: true is set in the frontmatter if you want the rule applied to every chat.
  4. Reinforce it in the request. For critical rules, a short reminder in the prompt (“remember, no grep, use PowerShell equivalents”) helps a lot.
  5. Split rules up. Instead of one big file with multiple instructions, create focused rules, like one for OS commands and another for language or comments.

Related topic about extra context: Cursor Agent not following RULES

The team is aware of the compliance gap. Your report helps with prioritization, but there isn’t a guaranteed fix since this comes from how LLMs process instructions. Still, the tips above should noticeably reduce how often the rules get broken.

2 Likes