Skip to content
Prompt

brigid — Cursor Rules

by Brigid-DICOM

AI Summary

A Cursor IDE rule set that enforces mandatory memory tool usage for context-aware AI assistance, helping developers maintain conversation continuity when working with external systems and previous project work.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "brigid — Cursor Rules" prompt rules to my project.
Repository: https://github.com/Brigid-DICOM/brigid

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

An learning project demonstrating modern Web-based DICOM/PACS architecture. Built with Next.js and Hono, featuring DICOMweb, DIMSE, and professional image viewing.

⚠️ CRITICAL: MEMORY TOOLS ARE MANDATORY ⚠️

ALWAYS EVALUATE FIRST: Before responding to ANY user request, assess whether you have sufficient context: • CONTEXT ASSESSMENT: When facing a request that references: • External systems or integrations (like "integrate with X") • Previous work or conversations not in current context • Project-specific concepts not explained in the current query • Any continuation of previous tasks Search memory when you might lack necessary context. WHEN IN DOUBT, SEARCH - it's better to check unnecessarily than miss critical context. Only skip searching when the query is completely self-contained. KEY TRIGGER PHRASES requiring immediate search_keys or search_memory: • "we need to integrate with..." • References to previous work ("I added X, now we need to...") • Mentions of specific systems without context • Any request mentioning recent discussions that you don't know about or about continuing previous work • LAST ACTION: Store memory of significant interactions using store_memory. NEVER store the full request-response; ONLY summaries, highlights and importnant pieces of information.

Overview

This guide explains how to effectively use the memory tools for storing, retrieving, and utilizing conversation context in agent mode.

Metadata Usage

Use metadata to track: • Importance of information • Related topics for cross-referencing • Categories for organizing memories • Temporal information (expiration, relevance period)

1. SEARCH WHEN CONTEXT MIGHT BE MISSING

Search memory when there's any indication you might need additional context: • Use the search_keys or search_memory tool when you have uncertainty • Search if there's any chance the user is referencing previous work, discussions, or context • Search when the user refers to previous work, decisions, or information not present in the current conversation • Construct a query related to the specific missing context • Analyze the returned results for relevant context • Remember: It's better to search unnecessarily than miss critical context

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1mo ago
Active
AdoptionUnder 100 stars
0 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Issues0
Updated1mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more