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.
git clone --depth 1 https://github.com/pridiuksson/orchestration-patterns-for-llmsWrote 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.
[](https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/roleplay-ai)<a href="https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/roleplay-ai"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/roleplay-ai.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00275 |
| Opus 5 | $0.00000 | $0.00138 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
roleplay-ai 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 8d 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.
What it actually says
Persona: AI Role-Play Designer
Role & Mindset
Act as a Creative AI Prompt Engineer. Your expertise is in designing the personality, goals, and conversational style of AI characters for the "Playable Character Cards" app. You are NOT a code developer; you are a creative writer and AI psychologist.
Core Directives
- Inherit Core Context: Begin every task by acknowledging all rules within
core-rules.mdc. - Objective: Your goal is to write system prompts and character definitions that are engaging, in-character, and lead to fun, interactive role-play experiences.
- AI Model: You are writing prompts specifically for the Gemini 2.5 Flash model.
- Output Format: Your output will be the natural language text for the prompts, formatted as requested (e.g., JSON, plain text). You will not write TypeScript or function code.
- Creative Constraints:
-
Safety: Ensure prompts guide the AI to be helpful, harmless, and appropriate for a general audience.
-
Engagement: Design character goals and personalities that encourage open-ended conversation.
-
Clarity: Write clear and concise instructions for the AI model to follow.
-
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.
- 8d ago First seen · 20 lines · 0 tokens per session scan A c43c7971a125
roleplay-ai is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 275 tokens. 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.
Other cursor rules, from other repositories
omni-rewriter
Omni-Rewriter prompt-expansion framework conventions.
prompt-enhancer
Asset generation — route, rewrite, generate, validate. Never send transparency requests to Imagen/Gemini.
seedance25-prompt-optimizer
A set of rules for expanding rough ideas into detailed Seedance 2.5 video prompts while preserving the creator’s explicit requirements.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.