project-guidelines

A set of project rules for a Cursor-based marketing operations workspace, covering lead research, search-engine audits, campaign analysis, competitor research, content, and reports.

In plain words
What is it for?
It helps carry out marketing research, enrich leads, review SEO, analyze campaigns, study competitors, create content, and prepare reports.
Why use it?
It gives agents a shared way to handle multi-step marketing work for non-technical users and says how web data and planning should be handled.

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/maccman/growth-agents/project-guidelines
Clone the repo
git clone --depth 1 https://github.com/maccman/growth-agents

Made for: Cursor.

Per session 760 This file is loaded in full into every session.
When invoked 760 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 $0.00760 $0.00760
Opus 5 $0.00380 $0.00380
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 2d ago against content hash 14b1a70fd153, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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/project-guidelines.mdc · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Growth Agents - Project Guidelines

Project Overview

This is a marketing ops and growth automation playground powered by Cursor AI. Agents are designed to perform complex, multi-step marketing tasks including lead enrichment, SEO audits, campaign analysis, content generation, competitive intelligence, and reporting.

Users interact with agents through Cursor's Chat to direct marketing tasks.

Assume users are non-technical marketing ops and growth leaders. Be friendly, skip jargon, and never ask them to run terminal commands or choose a programming language — just handle it.

Agent Development Process

  1. Planning First: Always come up with a good plan before executing any task. You MUST get sign off on the plan from the user before continuing.
  2. Write and run typescript or python code: Write and run typescript/python code to test your ideas. For anything that is best done programmatically, like math or other types of logic, then just write a quick TypeScript/python program and run it.
  3. ALWAYS prefer running executables vs writing scripts: Running executables is faster than writing scripts.
  4. Data from the web: Use the web_search and mcp_browsermcp tools to get data from the web. Never use the mcp_browsermcp tool to Google search - you should use the dedicated web_search tool for that as it's more reliable.
  5. Use unix principles: Use unix principles to build your scripts. Use stdin and stdout. Use | to chain commands together.
  6. Stream output: Stream output to the console. e.g. when processing CSVs, output line by line.
  7. Never alter a file in the data/ directory in-place: Always either produce a copy or, if you're editing textual data, use stdin and stdout to edit the data.

AI SDK

To communicate with AI providers, use the Vercel AI SDK.

  • Use Vercel AI SDK: Use the AI SDK directly with providers like @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/google
  • No Custom Abstractions: Don't create custom AI client wrappers - use the SDK directly
  • Environment variables for AI providers are automatically handled by Vercel AI SDK
  • No need to manually check or validate API keys in code
  • Standard variables: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY

Read the full file on GitHub · 60 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 · 60 lines · 760 tokens per session scan A 14b1a70fd153

Subscribe to this mod's changes

project-guidelines is a cursor rule published in the GitHub repository maccman/growth-agents (5 stars, last pushed 6mo ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 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.