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.
npx agentmods add rules/mjdevaccount/aistack-mcp/cursorrulesgit clone --depth 1 https://github.com/mjdevaccount/AIStack-MCPWhat 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 | $0.02545 | $0.02545 |
| Opus 5 | $0.01273 | $0.01273 |
| Sonnet 5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
cursorrules 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.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIStack Development Standards
Project Context
You have access to the codebase via MCP protocol with these tools:
- filesystem: Read/write/search files (including .env files)
- git: View history and changes
- github: Check PRs and issues
- sequential-thinking: Break down complex tasks
- brave-search: Research best practices
Environment Files
You CAN and SHOULD read .env files when needed:
.envfile is explicitly allowed in.cursorignore- Use it to read API keys, tokens, and configuration values
- This is necessary for setting up MCP servers and services
- Example: Reading
GITHUB_PERSONAL_ACCESS_TOKENfrom.envto configure GitHub MCP server
MCP Usage Guidelines
When to Use MCP Tools
- Understanding Context: Use filesystem to read related files
- Pattern Matching: Search for similar implementations
- Change History: Use git to understand why code exists
- Research: Use brave-search for best practices
- Complex Tasks: Use sequential-thinking to plan approach
Token Optimization
- Read only necessary files (ask which files before reading)
- Use git log with --oneline for quick history
- Summarize large files before suggesting changes
- Prefer targeted searches over reading entire directories
MCP Environment Self-Test
Before starting work, verify the MCP environment is properly configured:
# Quick self-test of MCP environment
python scripts/test_mcp_environment.py
# Verbose output with details
python scripts/test_mcp_environment.py --verbose
# Test specific server only
python scripts/test_mcp_environment.py --server aistack-intelligence
What the self-test discovers automatically:
- MCP servers configured in
.cursor/mcp.json - Service dependencies (Ollama, Qdrant, etc.) from environment variables
- Service health checks (HTTP endpoints)
- Server configuration validation
- Workspace accessibility
The script follows SOLID principles:
- Single Responsibility: Each checker handles one concern
- Open/Closed: Easy to add new service checkers without modifying existing code
- Liskov Substitution: All checkers implement consistent interface
- Interface Segregation: Separate concerns (discovery, checking, reporting)
- Dependency Inversion: Depends on configuration abstraction, not hardcoded values
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.
- yesterday First seen · 421 lines · 2,545 tokens per session scan A 0eeda2bcc097
cursorrules is a cursor rule published in the GitHub repository mjdevaccount/AIStack-MCP (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,545 tokens to every session, about $0.0127 per session on Opus 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.
Other cursor rules, from other repositories
cursorrules
Robot control server. Do not move the physical robot without checking health first.
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.