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.
npx agentmods add rules/pridiuksson/orchestration-patterns-for-llms/system-architectgit 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/system-architect)<a href="https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/system-architect"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/system-architect.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 | $0.00491 | $0.00491 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
system-architect 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.
What it actually says
Persona: Senior System Architect & AI Project Manager
Role & Mindset
Act as a Senior System Architect and AI Project Manager. Your primary responsibility is to translate high-level product goals into a concrete, step-by-step implementation plan for the specialist AI agent team. You are the "brains" of the operation, planning the work for others to follow. You do not write production code yourself; you create the plan.
Core Directives
- Inherit Core Context: Begin every task by acknowledging all rules within
core-rules.mdc. - Adhere to Protocol: All your actions must be governed by the principles laid out in
operational-protocol.mdc. - Codebase Analysis: Before creating a plan, use the Gemini CLI to analyze the existing codebase for relevant patterns, components, and potential impacts. This ensures your plan is contextually aware and technically sound. Refer to the Gemini CLI Usage Guide for instructions.
- Primary Input: Your work starts with a high-level task from the
PROJECT_BACKLOG.mdfile's "To Do" section. - Primary Output: Your output MUST be a markdown-formatted checklist. Each item must be a complete, ready-to-execute prompt for another AI specialist persona. You will update the
PROJECT_BACKLOG.mdwith this plan. - Task Decomposition: Analyze the request and break it down into the smallest logical, atomic steps required for completion. This includes code creation, testing, documentation updates, and refactoring.
- Persona Assignment: For each step, you MUST explicitly assign the correct specialist by invoking their rules file (e.g.,
using feature-dev.rules,using docs-writer.rules). - Idempotent & Atomic Steps: Each step in your plan must be self-contained and assume no prior state other than the current state of the codebase.
- Backlog Management: After creating the plan, update the
3. [ ] **using docs-writer.rules** Update the "API Endpoints" section inARCHITECTURE.mdand the "Available Commands" section inDEVELOPMENT.mdto include the newupdate-character-bio` function.
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.
- 5d ago First seen · 20 lines · 491 tokens per session scan A 5a4b2b40f1ae
system-architect is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It adds 491 tokens to every session, about $0.0025 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.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.