guidelines

A general set of coding and assistant-behavior guidelines covering clarity, testing, documentation, architecture, and project context.

In plain words
What is it for?
Use it when generating or reviewing production code, checking style and architecture, or loading project-specific conventions before making changes.
Why use it?
It gives code generation a consistent standard and encourages it to follow the existing codebase instead of inventing unrelated patterns.

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/levifig/rails-instructions/guidelines
Clone the repo
git clone --depth 1 https://github.com/levifig/rails-instructions

Made for: Cursor.

Per session 633 This file is loaded in full into every session.
When invoked 633 The same file — it is already loaded in full.
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 $0.00633 $0.00633
Opus 5 $0.00316 $0.00316
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00063 $0.00063

Measured yesterday against content hash aa8e275b7bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.cursor/rules/guidelines.mdc · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor AI Assistant Rules

Assistant Behavior

  • Be terse and direct in responses
  • Ask clarifying questions before implementing complex features
  • Anticipate needs and suggest improvements proactively
  • Focus on high-quality, production-ready code
  • Use analogies when explaining complex concepts

Code Generation Principles

Quality Standards

  • Generate code that could ship to production
  • Follow established patterns in the codebase
  • Maintain consistency with existing architecture
  • Every piece of code should be testable
  • Documentation is not optional

Style Guidelines

  • Respect .prettierrc and linting configurations
  • Prefer clarity over cleverness
  • Use descriptive names that reveal intent
  • Keep line lengths reasonable
  • Consistent indentation and formatting

Architecture Focus

  • Think in systems, not just functions
  • Consider scalability implications
  • Design for maintainability
  • Separate concerns appropriately
  • Make dependencies explicit

Project Awareness

Context Loading

Always check for .cursor/PROJECT_CONTEXT.md which contains:

  • Current architectural patterns
  • Technology stack decisions
  • Team conventions and preferences
  • Recent design decisions
  • Performance considerations
  • Known technical debt

File Organization

  • Follow existing project structure
  • Keep related code together
  • Use standard naming conventions
  • Maintain clear module boundaries

Code Patterns

Error Handling

  • Fail fast with clear messages
  • Use appropriate error types
  • Handle errors at the right level
  • Provide actionable error messages
  • Log errors appropriately

Testing Approach

  • Write tests alongside implementation
  • Test edge cases explicitly
  • Use descriptive test names
  • Keep tests simple and focused
  • Mock external dependencies

Documentation

  • Document why, not what
  • Include examples for complex APIs
  • Keep docs in sync with code
  • Use consistent documentation format
  • Document assumptions and constraints

Language-Specific Rules

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 633 tokens per session scan A aa8e275b7bac

Subscribe to this mod's changes

guidelines is a cursor rule published in the GitHub repository levifig/rails-instructions (54 stars, last pushed 1y ago), licensed MIT. It adds 633 tokens to every session, about $0.0032 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.