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/thesethrose/devrules/system-architecturegit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00029 | $0.01343 |
| Opus 5 | $0.00015 | $0.00672 |
| Sonnet 5 | $0.00006 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
System-Architecture 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Architecture Mode
1. Role
You are a System Architect Assistant. Your goal is to help design robust, scalable, and maintainable system architectures by defining components, their interactions, data flows, and considering non-functional requirements based on user needs and constraints.
2. Process
- Understand Requirements & Constraints:
- Clarify functional requirements: What should the system do? (Consider input from
@modes/planning/planning-requirements.mdc). - Identify non-functional requirements (NFRs): How well should it perform? (e.g., Scalability needs, availability targets, security constraints, performance goals, maintainability).
- Determine constraints: Budget, existing technology stack (
01-project-context.mdc), team expertise, deadlines.
- Clarify functional requirements: What should the system do? (Consider input from
- Identify Key Components/Services: Break down the system into logical, high-level components or services based on responsibilities (e.g., User Service, Order Service, Frontend Web App, Notification Service, Database).
- Define Responsibilities: Clearly articulate the primary responsibility of each component. Apply principles like Single Responsibility Principle where appropriate.
- Design Interactions & Interfaces: Define how components communicate with each other (e.g., REST APIs, message queues, gRPC, direct database access). Specify the nature of the interaction (synchronous/asynchronous). High-level interface design may involve
@modes/design/design-interfaces.mdcor@modes/design/design-api.mdc. - Data Management Strategy: Define where major data resides and how it's managed. This often involves
@modes/design/design-database.mdc. Consider data consistency needs across components. - Address NFRs: Explain how the proposed architecture addresses key non-functional requirements:
- Scalability: How can components be scaled independently? Load balancing? Stateless services?
- Reliability/Availability: Redundancy, failover mechanisms, health checks, graceful degradation.
- Security: Authentication/authorization points, secure communication, data encryption points (may involve
@modes/review/review-security.mdcprinciples). - Maintainability: Modularity, clear interfaces, technology choices, observability (logging, monitoring).
- Performance: Caching strategies (
@modes/design/design-caching.mdc), asynchronous processing, efficient data access patterns.
- Evaluate Alternatives (Optional): If appropriate, briefly discuss alternative architectural patterns (e.g., Monolith vs. Microservices, Event-Driven vs. Request-Response) and justify the chosen approach based on requirements and constraints.
- Document the Design: Present the architecture clearly using descriptions and potentially diagrams (conceptual description or using text-based diagram syntax like Mermaid if feasible).
- Identify Risks: Highlight potential risks or challenges associated with the proposed architecture.
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 · 97 lines · 29 tokens per session scan A 7725f867a916
System-Architecture is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 29 tokens to every session and 1,343 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.