architecture

A command for designing software architecture from a user story and the project’s constraints. Software architecture is the high-level structure of a system and the way its major parts work together.

In plain words
What is it for?
Use it to compare three possible designs, choose a lower-risk option, plan proof-of-concept experiments, and record decisions in architecture decision records, or ADRs.
Why use it?
It makes important design choices explicit and surfaces trade-offs, security concerns, legacy-system effects, and unknowns before implementation begins.

Skill for Claude CodeCodexCursor

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 skills/usrrname/cursorrules/architecture
Any agent
npx skills add usrrname/cursorrules --skill architecture
Clone the repo
git clone --depth 1 https://github.com/usrrname/cursorrules

Made for: Claude Code, Codex, Cursor.

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,625 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00009 $0.01625
Opus 5 $0.00005 $0.00813
Sonnet 5 $0.00002 $0.00325
Haiku 4.5 $0.00001 $0.00162

Measured 2d ago against content hash 39f540ec0f70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.cursor/skills/architecture/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Design Command 🏗️

This command guides the AI architect agent to analyze user stories and propose multiple architectural solutions following a structured workflow.

Critical Rules

  • Always start with understanding the user's request, the user story, existing constraints, existing architecture, and its business context. Ask clarifying questions to ensure a complete understanding.
  • Propose 3 viable solutions. One should be the simplest of the lowest-risk.
  • Consider both functional and non-functional requirements
  • Offer trade-offs if the user requests them; evaluate trade-offs systematically
  • Consider security implications in terms of OWASP Top 10
  • Consider impact on existing architecture, if there are any existing .cursor/.ai/architecture/ files
  • Recommend spikes or proof-of-concepts to validate solutions against system and business constraints
  • Evaluate impact on legacy systems (if any) or decisions that are already in place
  • Document architectural decisions (ADRs) using .cursor/rules/templates/architecture-decision-record.md
  • Architecture document filename conventions:
    • high-level-architecture.md - shows architecture at system level and the different parts that constitute a solution
    • solution_proposal.md or spike_#.md - should be created as part of a spike task for a problem and stored in .cursor/.ai/spikes/

Workflow Phases

1. Story Analysis

  • Clarify business objectives
  • Extract functional requirements
  • Identify non-functional requirements
  • Define constraints and assumptions
  • Identify stakeholders
  • Map dependencies on legacy systems
  • Understand team capabilities and preferences

2. Solution Generation

  • Include simple diagrams to illustrate the proposed solutions
  • Propose 3 architectural approaches
  • Consider different architectural styles
  • Evaluate emerging technologies and widely used industry choices based on prior art or best practices by SaaS companies
  • Situate the solution in context of the current business and technical constraints and opportunities. (In all likelihood, you are not working at a Big Tech company, and pre-existing SaaS practices will not always be applicable)
  • Include up to 5 web-based sources that support the proposed solutions
  • Consider build vs. buy options
  • Consider open source vs. proprietary solutions
  • Assess legacy system integration points

Read the full file on GitHub · 258 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. 2d ago First seen · 258 lines · 9 tokens per session scan A 39f540ec0f70

Subscribe to this mod's changes

architecture is a skill published in the GitHub repository usrrname/cursorrules (10 stars, last pushed 4mo ago), licensed ISC. It adds 9 tokens to every session and 1,625 once invoked, about $0.0000 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.