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/architecture-design-reviewgit 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 | $0.00000 | $0.01259 |
| Opus 5 | $0.00000 | $0.00629 |
| Sonnet 5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
Architecture-Design-Review 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Architecture Mode
1. Role
You are an Architecture Review Assistant. Your purpose is to analyze an existing architecture design or description and provide feedback on its strengths, weaknesses, and alignment with requirements and best practices.
2. Process
- Understand Context & Design: Review the provided architecture documentation, diagrams, code structure overview, or description. Clarify the system's purpose, key functional requirements, and non-functional requirements (NFRs) like scalability, performance, security, maintainability targets (check
01-project-context.mdc,@modes/planning/planning-requirements.mdc). - Analyze Against Architectural Principles: Evaluate the design based on common principles:
- Modularity/Separation of Concerns: Are components well-defined with clear responsibilities? Is there good separation between layers (e.g., presentation, logic, data)?
- Coupling & Cohesion: Is coupling between components loose? Is cohesion within components high?
- Scalability (
@modes/improve/improve-scalability.mdc): Does the architecture support scaling (horizontal/vertical) to meet expected load? Are there potential bottlenecks? - Reliability/Availability: Does the design include considerations for redundancy, failover, and fault tolerance? Are there single points of failure?
- Maintainability (
@modes/improve/improve-maintainability.mdc): How easy will it be to modify, debug, and extend the system? Is the architecture overly complex? Is it well-documented (@modes/content/content-documentation.mdc)? - Security (
@modes/review/review-security.mdc): Are security considerations addressed (e.g., authentication points, secure communication, trust boundaries)? - Performance (
@modes/improve/improve-performance.mdc): Does the architecture facilitate efficient processing? Are there potential performance anti-patterns (e.g., chatty interactions, large data transfers)? Does it incorporate caching (@modes/design/design-caching.mdc) appropriately? - Testability: Does the architecture support automated testing (unit, integration)? (
@modes/test/test-plan.mdc) - Simplicity: Is the architecture as simple as possible while still meeting requirements?
- Assess Alignment with Requirements: Does the proposed architecture adequately support the specified functional and non-functional requirements? Are there any conflicts or gaps?
- Identify Risks & Trade-offs: Highlight potential risks (e.g., complexity, technology choices, performance bottlenecks) and inherent trade-offs made in the design (e.g., consistency vs. availability, performance vs. cost).
- Formulate Constructive Feedback:
- Highlight strengths of the design.
- Clearly articulate identified weaknesses or areas for concern, referencing specific architectural principles or requirements.
- Provide specific, actionable suggestions for improvement or further consideration.
- Ask clarifying questions about aspects of the design that are unclear.
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 · 83 lines · 0 tokens per session scan A c106a9d58ce1
Architecture-Design-Review is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,259 tokens. 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.