cursorrules

Instructions for processing prompt decorators: annotations beginning with +++ that change how an AI handles a request.

In plain words
What is it for?
Handling prompts that use decorators such as +++Reasoning and applying their requested response or coding behavior.
Why use it?
It defines how to detect decorators, read their options, and apply several decorators in order without losing the original request.

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/synaptiai/prompt-decorators/cursorrules
Clone the repo
git clone --depth 1 https://github.com/synaptiai/prompt-decorators

Made for: Cursor.

Per session 23,596 This file is loaded in full into every session.
When invoked 23,596 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 88% 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 $0.23596 $0.23596
Opus 5 $0.11798 $0.11798
Sonnet 5 $0.04719 $0.04719
Haiku 4.5 $0.02360 $0.02360

Measured 2d ago against content hash e9ea8af2c7c4, 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.

Origin

This is a copy

88% identical to 900-software-dev-decorators — 761 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.

.cursorrules · 2,611 lines

How it starts

The opening of the file, as written. The whole thing — 2,611 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Decorators Processing Instructions

Overview

As an AI language model, you must identify and process "Prompt Decorators" in user queries. A Prompt Decorator is an annotation that begins with +++ followed by a name and optional parameters that modifies how prompts are generated and structured. When you detect these decorators in a user's input, apply the corresponding transformation instructions to enhance your response.

This document defines all supported decorators, their parameters, and how to transform the prompt when they are detected. You must parse and apply these rules whenever you encounter decorators in user input.

Decorator Detection and Application Process

  1. When receiving a user prompt, scan for patterns matching +++DecoratorName(parameters) at the beginning of lines
  2. For each detected decorator, apply its transformation instruction to modify your processing approach
  3. When multiple decorators are present, apply them in the order they appear
  4. Maintain the core query intent while applying the decorator-specific modifications to your response style, structure, and content

Core Prompt Decorators

+++Reasoning

When this decorator is included in a prompt, the response must provide explicit reasoning paths before reaching conclusions. This makes the thinking process transparent.

Parameters:

  • depth (basic | moderate | comprehensive): Controls the detail level of reasoning
    • basic: Focus on the most important logical steps
    • moderate: Balance detail with clarity
    • comprehensive: Provide thorough analysis with multiple perspectives

Transformation Instruction: "Please provide detailed reasoning in your response. Show your thought process before reaching a conclusion. [depth-specific instruction]"

Example:

+++Reasoning(depth=comprehensive)
What are the implications of quantum computing for cybersecurity?

+++StepByStep

When this decorator is present, the response must be structured as a sequence of clearly labeled steps, making complex processes more digestible.

Read the full file on GitHub · 2,611 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 · 2,611 lines · 23,596 tokens per session scan A e9ea8af2c7c4

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository synaptiai/prompt-decorators (43 stars, last pushed 8d ago), licensed Apache-2.0. It adds 23,596 tokens to every session, about $0.1180 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to 900-software-dev-decorators, differing in 761 lines, and is treated as a copy.