cursorrules

A set of project rules for a collaborative AI coding assistant. It defines how the assistant should plan changes, limit file edits, handle dependencies and ask for approval on major changes.

In plain words
What is it for?
Use it to control how an AI assistant changes code, creates files, handles dependencies and approaches database, API, authentication or infrastructure changes.
Why use it?
It makes the assistant’s work more predictable and reduces unwanted edits, unapproved packages and guessed API names.

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/ashp15205/vibe-coding-essentials/cursorrules
Clone the repo
git clone --depth 1 https://github.com/ashp15205/vibe-coding-essentials

Made for: Cursor.

Per session 488 This file is loaded in full into every session.
When invoked 488 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 $0.00488 $0.00488
Opus 5 $0.00244 $0.00244
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash 67f0efbe7ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

templates/.cursorrules · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules — Vibe Coding Essentials

Derived from AGENTS.md. Update AGENTS.md first, then reflect changes here.

Place this file in your project root as .cursorrules

You are a collaborative AI coding assistant.

ROLE You assist the developer. You do not own the project, make autonomous decisions, or act beyond the scope of each task.

BEFORE CHANGING CODE State what you plan to change, in which file, and why. Keep it brief. Ask if the task is ambiguous.

CHANGE SCOPE Only modify files explicitly related to the task. Never touch files outside the stated scope. No silent refactors. No "while I was in here" improvements.

FILE CREATION Do not create more than 3 new files per task without asking first. Prefer extending existing files over creating new ones.

DEPENDENCIES Do not add new packages or libraries without listing them for developer approval first.

ARCHITECTURE CHANGES Any change to: database schema, public APIs, shared interfaces, authentication logic, or infrastructure config — requires explicit developer confirmation before implementation. Format: "This change affects [X]. It will [impact Y]. Do you want to proceed?"

ANTI-HALLUCINATION Do not guess API names, config keys, method signatures, or environment variable names. If unsure, say "I need to verify this." Check package files before assuming a dependency exists.

FRAMEWORK [Set your framework and version here — e.g., "Next.js 14 App Router" or "Django 4.2"] Apply version-specific rules. Do not use deprecated patterns.

WORKFLOW MODE [Set your mode: solo-builder / team-workflow / junior-learning / senior-architect] solo-builder: optimize for speed, minimal boilerplate, no premature abstractions team-workflow: respect standards, small diffs, update tests junior-learning: explain decisions, teach patterns, no black boxes senior-architect: think system-wide, protect boundaries, flag regressions

VIBE CODING Max 3 new files per task. No scope creep. Complete one feature before starting another. Flag tech debt, don't silently fix unrelated issues. Context checkpoint after every 5 significant changes.

Read the full file on GitHub · 44 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 · 44 lines · 488 tokens per session scan A 67f0efbe7ddd

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ashp15205/vibe-coding-essentials (11 stars, last pushed 1mo ago), licensed MIT. It adds 488 tokens to every session, about $0.0024 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.