core-rules

core-rules is a cursor rule for Cursor from pridiuksson/orchestration-patterns-for-llms. It costs 654 tokens per session, scanned A, original, MIT.

Project rules for building Playable Character Cards, a social network for AI-generated character mini-games. They define the project’s priorities, documentation path, and architectural principles.

In plain words
What is it for?
Use them on tasks in that project so implementation follows its required stateless functions, shared AI adapter, and code-first documentation approach.
Why use it?
They give an agent the project context and tell it which documents and design rules to consult before changing code.

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/pridiuksson/orchestration-patterns-for-llms/core-rules
Clone the repo
git clone --depth 1 https://github.com/pridiuksson/orchestration-patterns-for-llms

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 core-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/core-rules.svg)](https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/core-rules)
Your own site
<a href="https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/core-rules"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/core-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 654 This file is loaded in full into every session.
When invoked 654 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 $0.00654 $0.00654
Opus 5 $0.00327 $0.00327
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00065 $0.00065

Measured 4d ago against content hash 9b7444ae3317, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-rules 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 4d 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.

examples/playable-character-cards-rules/.cursor/rules/core-rules.mdc · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core System Rules & Foundational Context

1. Primary Objective

Your primary objective is to assist in building "Playable Character Cards," a social network for AI-generated character mini-games. Always align your work with this Core Vision.

2. The Single Entry Point: agents.md

The agents.md file is your single source of truth for navigation. It is the only file you need to read first.

You MUST begin every task by consulting agents.md to find the correct documentation for your task:

  • DEVELOPMENT.md: For all "how-to" instructions (build, test, run, troubleshoot).
  • ARCHITECTURE.md: For all "what and why" questions (principles, design, philosophy).
  • /ADR: For specific, detailed architectural decisions.

3. Architectural Principles

You must strictly adhere to the project's core principles as defined in ARCHITECTURE.md and the detailed decisions in the /ADR/ directory. Key principles include:

  • Statelessness: All Edge Functions must be stateless.
  • AI Adapter Pattern: All AI model calls must go through a shared adapter.
  • Code-First Documentation: The code is the truth; documentation must only point to it.
  • Real API Testing: Tests must use real APIs, never mocks.

4. 🔒 CRITICAL SECURITY REQUIREMENTS

NEVER compromise security credentials under ANY circumstances:

4.1 Absolute Prohibitions

  • NEVER include actual passwords, API keys, or secrets in code, documentation, comments, or examples.
  • NEVER commit real credentials to git history.
  • NEVER use production secrets as examples.

4.2 Required Security Patterns

  • Always use placeholders: YOUR_SECRET_HERE, [REDACTED].
  • Always reference environment variables: Deno.env.get('ADMIN_SECRET_KEY').
  • Always validate before commit: Search for any real credentials before committing.

5. Technical Constraints

  • Dependency Management: All Deno dependencies MUST be managed via /supabase/import_map.json.
  • Official SDKs Only: You MUST use the official Google AI SDK through the established AI adapter pattern. Do not use fetch() to call the Gemini API.
  • Defensive Parsing: Always assume Gemini responses may be wrapped in markdown and parse them defensively.

Read the full file on GitHub · 49 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. 4d ago First seen · 49 lines · 654 tokens per session scan A 9b7444ae3317

Subscribe to this mod's changes

core-rules is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 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.