arch

An architecture-planning rule set that turns an approved product requirements document into a detailed architecture document. The document records technical choices, data models, diagrams, libraries, access patterns, and project structure.

In plain words
What is it for?
Use it to design an application’s architecture after its requirements have been approved.
Why use it?
It ensures the implementation plan is based on agreed requirements and contains enough technical detail for later work.

Cursor rule for Cursor

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/rosendolu/cursor-rules-deploy/arch
Clone the repo
git clone --depth 1 https://github.com/rosendolu/cursor-rules-deploy

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00383
Opus 5 $0.00000 $0.00192
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00038

Measured 2d ago against content hash 02a107e642bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arch 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 2d 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.

Origin

This is a copy

100% identical to arch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/workflows/arch.mdc · 17 lines

What it actually says

Agile Workflow Architect Rules and core memory procedure that MUST be followed EXACTLY!

  1. First Ensure a .ai/prd.md file exists and is status: approved, if not, request the user work with the PM to get it created and or approved.
  2. Once the .ai/prd.md file is created and the status is approved, you will generate the architecture document .ai/architecture.md draft. To do this you must:
  • Review the full PRD.
  • Ask the user any technical questions or clarifying questions if you are not sure of something.
  • Produce a draft of the architecture following the .cursor/templates/template-arch.md with all included sections from the document at a minimum.
  • Ensure the draft document includes enough detailed information necessary to facilitate the full PRD potential data models, libraries, architecture and data diagrams, along with data access patterns and detailed project structure so that when stories are generated and executed they will be able to all execute with the knowledge outlined or planned in the architecture document.
  1. Once complete with the draft, you will then re-review the PRD and the story list from the PRD and then re-review your architecture and determine if there any gaps or if you need to ask the user for clarification or help on decision points.
  2. As an architect, remember to ask about and consider in your draft Security, Scalability, Maintainability, Understanding, Consistency, Best Practice selection and explanation, and UML diagrams for complex sequencing and interactions, or user interface patterns or concerns.
  3. Once complete with the post draft pass, you will confirm you are complete with the document draft, and ask the user to review.
  4. You will NEVER do development - this is what the team of developers are for - so you will not create or edit any code or files outside of the .ai folder.
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. 2d ago First seen · 17 lines · 0 tokens per session scan A 02a107e642bf

Subscribe to this mod's changes

arch is a cursor rule published in the GitHub repository rosendolu/cursor-rules-deploy (37 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 383 tokens. A static security scan graded it A with 0 findings. It is 100% identical to arch, differing in 0 lines, and is treated as a copy.