sre-ai-rules

sre-ai-rules is a cursor rule for Cursor from SmythOS/sre. It costs 1,278 tokens per session, scanned A, original, MIT.

A set of development rules for the SmythOS SRE monorepo, a single repository containing multiple related parts of the Smyth Runtime Environment. It documents architecture patterns for connectors, access control, storage, vector databases, caching, and agent services.

In plain words
What is it for?
Use it when modifying or reviewing SmythOS SRE code, especially connector implementations and operations protected by access-control rules.
Why use it?
It gives coding agents project-specific conventions that are not obvious from an individual file. This helps keep changes consistent with the repository’s interfaces, permissions, and ownership rules.

Cursor rule for Cursor

About the project

SmythOS Runtime Environment is an open-source runtime and software development kit for building and running AI agents. Developers use it to create, orchestrate, and manage agents across local, cloud, and edge environments, with abstractions for language models, vector databases, storage, and caching. The catalogue add-ons support work with this runtime.

SmythOS/sre · 1,289 stars · on GitHub

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/smythos/sre/sre-ai-rules
Clone the repo
git clone --depth 1 https://github.com/SmythOS/sre

Made for: Cursor.

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.

agentmods badge for sre-ai-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/smythos/sre/sre-ai-rules.svg)](https://agentmods.dev/rules/smythos/sre/sre-ai-rules)
Your own site
<a href="https://agentmods.dev/rules/smythos/sre/sre-ai-rules"><img src="https://agentmods.dev/badge/rules/smythos/sre/sre-ai-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,278 This file is loaded in full into every session.
When invoked 1,278 The same file — it is already loaded in full.
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 $0.01278 $0.01278
Opus 5 $0.00639 $0.00639
Sonnet 5 $0.00256 $0.00256
Haiku 4.5 $0.00128 $0.00128

Measured 5d ago against content hash b5a18a51dae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sre-ai-rules 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 5d 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/sre-ai-rules.mdc · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SmythOS SRE Monorepo - Cursor AI Rules

Project Overview

This is the SmythOS SRE (Smyth Runtime Environment) monorepo - an advanced agentic AI platform that provides a comprehensive runtime environment for building and managing AI agents. The system includes LLM management, vector databases, storage, security, and agent orchestration capabilities.

Core Architecture Patterns

Connector Pattern (Primary Design)

  • Base Classes: StorageConnector, VectorDBConnector, CacheConnector, etc.
  • Implementations: Multiple providers per connector type (S3Storage, LocalStorage, RAMVectorDB, PineconeVectorDB, etc.)
  • Interface: All connectors expose .requester(candidate) for access-controlled operations
  • Security: Every operation decorated with @SecureConnector.AccessControl

Access Control System (ACL)

  • Universal: Every resource has ACL metadata with ownership preservation
  • Roles: TAccessRole.User, TAccessRole.Agent, TAccessRole.Team
  • Levels: TAccessLevel.Read, TAccessLevel.Write, TAccessLevel.Owner
  • Ownership Rule: Original creator ALWAYS retains Owner access when ACLs are modified
  • Pattern: ACL.from(acl).addAccess(candidate.role, candidate.id, TAccessLevel.Owner)

Monorepo Structure & Package Manager

  • Package Manager: PNPM (required) - use pnpm commands for all package management
  • Workspace Structure:
    • packages/core - Main runtime library (@smythos/sre)
    • packages/sdk - Developer SDK (@smythos/sdk)
    • packages/cli - Command line interface
    • examples/ - Example implementations and demos

Key Subsystems (packages/core/src/subsystems/)

  • IO: Storage, VectorDB, NKV, Router, CLI services
  • Security: ACL, Vault, Account management
  • LLMManager: Model providers, inference, embeddings
  • AgentManager: Agent orchestration, components, workflows
  • MemoryManager: Cache services

Naming Conventions & Standards

Read the full file on GitHub · 128 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.

  1. 5d ago First seen · 128 lines · 1,278 tokens per session scan A b5a18a51dae9

Subscribe to this mod's changes

sre-ai-rules is a cursor rule published in the GitHub repository SmythOS/sre (1,289 stars, last pushed 5mo ago), licensed MIT. It adds 1,278 tokens to every session, about $0.0064 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 2026-08-30.