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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00000 | $0.00110 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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
baml
A set of rules for setting up BAML and help with syntax guidance.
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
prompting-for-qe
Soạn/tinh chỉnh prompt cho tác vụ QE (sinh test case, phân tích requirement, tóm tắt tài liệu test, phân tích log) — đặc biệt khi output AI lan man, chung chung, bịa, hoặc muốn chốt prompt thành template tái dùng.
anthropic-chain-of-thought
Anthropic Chain of Thought and XML Tag Best Practices.