architecture-guidelines

architecture-guidelines is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 22 tokens per session (738 once invoked), scanned A, original, MIT.

A set of design rules for changes that cross modules, packages, services, APIs, or data storage.

In plain words
What is it for?
Use it for refactors, migrations, integrations, shared utilities, public interfaces, plugins, workflows, and other changes that affect multiple parts of a codebase.
Why use it?
It helps keep ownership clear, dependencies flowing in one direction, and new interfaces small and stable as a project grows.

Cursor rule for Cursor

Written for Cursor: installed under .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/oriolshhh/runware-image-mcp/architecture-guidelines
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

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 architecture-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/architecture-guidelines.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/architecture-guidelines)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/architecture-guidelines"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/architecture-guidelines.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 5.1 $0.00022 $0.00738
Opus 5 $0.00011 $0.00369
Sonnet 5 $0.00004 $0.00148
Haiku 4.5 $0.00002 $0.00074

Measured 2d ago against content hash 205aae7cf8f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

architecture-guidelines 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/rules/architecture-guidelines.mdc · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: architecture-guidelines

Architecture Guidelines

Purpose

Keep the repository's structure coherent as it grows. Use this skill to prevent feature work from creating tangled dependencies, unclear ownership, or short-term abstractions that become long-term drag.

When to use it

  • A change crosses modules, packages, services, commands, APIs, or persistence.
  • A task introduces a new abstraction, integration point, shared helper, data flow, public contract, or lifecycle.
  • A refactor, migration, plugin/extension point, workflow, or framework-level behavior is in scope.
  • Review finds duplicated ownership, circular dependencies, or unclear seams.

Instructions

  1. Map the current owners and dependency direction before editing. Identify the module that should own the behavior and the boundary that callers should use.
  2. Preserve one-way dependencies. Avoid circular imports, peer modules reaching into each other's internals, and "god" modules that know every subsystem.
  3. Design the smallest stable interface. Expose intent and domain terms, not storage details, framework internals, or incidental implementation choices.
  4. Keep policies and mechanisms separate. Business rules, validation, transport, storage, rendering, and orchestration should not collapse into one file when they change for different reasons.
  5. Prefer composition over inheritance/global registries unless the repository already has an established extension model.
  6. Make lifecycle and ownership explicit: who creates, mutates, caches, retries, cleans up, and invalidates each piece of state.
  7. For migrations and compatibility, define old/new behavior, transition path, fallback, rollback, and versioning expectations.
  8. Record non-obvious architectural tradeoffs in the spec, decision record, or a concise code comment near the boundary.
  9. Keep architecture changes incremental. If a broader cleanup is useful but not required, propose it separately instead of smuggling it into the diff.

Read the full file on GitHub · 74 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 · 74 lines · 22 tokens per session scan A 205aae7cf8f2

Subscribe to this mod's changes

architecture-guidelines is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 738 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 2026-09-03.