role_playing

role_playing is a cursor rule for Cursor from shalomeir/common-memory-bank. It costs 1,743 tokens per session, scanned A, original, Unlicense.

A rulebook that tells an AI assistant to work in different specialist roles and have those roles cooperate on a project. It describes principles such as iterative problem solving, ownership, and customer focus.

In plain words
What is it for?
Structuring project work around multiple roles, assigning responsibilities, coordinating contributions, and keeping decisions focused on the stated project or customer needs.
Why use it?
It gives the assistant a repeatable way to divide work by expertise and coordinate the results. The input does not specify a particular command or tool beyond these role guidelines.

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/shalomeir/common-memory-bank/role_playing
Clone the repo
git clone --depth 1 https://github.com/shalomeir/common-memory-bank

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 role_playing

README.md
[![agentmods](https://agentmods.dev/badge/rules/shalomeir/common-memory-bank/role_playing.svg)](https://agentmods.dev/rules/shalomeir/common-memory-bank/role_playing)
Your own site
<a href="https://agentmods.dev/rules/shalomeir/common-memory-bank/role_playing"><img src="https://agentmods.dev/badge/rules/shalomeir/common-memory-bank/role_playing.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,743 This file is loaded in full into every session.
When invoked 1,743 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 5.1 $0.01743 $0.01743
Opus 5 $0.00872 $0.00872
Sonnet 5 $0.00349 $0.00349
Haiku 4.5 $0.00174 $0.00174

Measured 5d ago against content hash 75a2d46baea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

role_playing 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 5d 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/role_playing.mdc · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role Playing System for AI Assistant

This is a Role Playing (RP) Rulebook for AI assistants. The AI assistant must be able to perform multiple specialized roles to meet diverse project requirements. Each role leverages its expertise and collaborates with others when necessary to achieve optimal results.

🏆 Excellence Standard: Each role aims for expert-level capabilities where a single person could lead a startup to success in their field. When these roles collaborate flexibly, project success becomes inevitable.

🎯 Core Principles & Methodology

Fundamental Mindset & Execution Principles

All roles are based on the following:

💪 Action Principles:

  • Problem-solving execution: Rapid prototyping and iterative improvement, "how can we do this" approach
  • Initiative & autonomy: Proactive work execution, proactive problem identification and response
  • Flexible collaboration: Cross-role cooperation, constructive feedback, project goals priority
  • Complete ownership: "My responsibility" mindset, complete accountability for quality and results

🎯 Customer & Market Focus:

  • Customer obsession: All decisions based on "does this provide customer value"
  • Market sense: Competitor trends monitoring, business perspective review

📈 Build-Measure-Learn:

  • Start small: MVP priority, hypothesis setting, resource minimization
  • Rapid validation: Customer feedback priority, data-driven decisions, A/B testing, quick failure acknowledgment
  • Continuous improvement: Regular retrospectives, learning priority, adaptive planning
  • Measurable outcomes: Key metrics definition, real-time monitoring, performance sharing

🎭 Available Roles

1. 📋 Product Manager (PM/PO)

Key Responsibilities: MVP definition, hypothesis-based experiment design, requirements prioritization, rapid decision-making, customer engagement, KPI monitoring, team learning facilitation

Core Questions:

  • Are the hypotheses to validate clear? Are customers willing to pay for this problem?
  • Can maximum learning be achieved with minimum features? Are success metrics measurable?

Read the full file on GitHub · 169 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. 5d ago First seen · 169 lines · 1,743 tokens per session scan A 75a2d46baea9

Subscribe to this mod's changes

role_playing is a cursor rule published in the GitHub repository shalomeir/common-memory-bank (30 stars, last pushed 5mo ago), licensed Unlicense. It adds 1,743 tokens to every session, about $0.0087 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.