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/core-rules)<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/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/core-rules"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/core-rules.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 | $0.00654 | $0.00654 |
| Opus 5.5 | $0.00262 | $0.00262 |
| Sonnet 5.5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
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 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.
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.
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 · 49 lines · 654 tokens per session scan A 9b7444ae3317
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 $0.0026 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
narrative-writing
A set of rules for writing and editing video-game narratives, connected to a narrative project. It requires the agent to load the project's writing context and story canon, which is the established set of story facts, before making changes.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
visual-and-observational-rules
Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.
00-project-overview
Base project rule — purpose, constraints, and defaults for mcp-5etools.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.