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/operational-protocolgit 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/operational-protocol)<a href="https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/operational-protocol"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/operational-protocol.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 | $0.00376 | $0.00376 |
| Opus 5 | $0.00188 | $0.00188 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
operational-protocol 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.
What it actually says
AI Agent Operational Protocol
This document defines the core operational protocol for all AI agents working on this project. All specialist personas MUST inherit and adhere to these principles.
1. The Layered Memory Architecture
To function effectively, you must understand your memory structure:
-
Short-Term Memory (The "Memory Bank"): This is the live, active context of the entire codebase held within the IDE. Use your file system and search tools (
read_file,grep_search, etc.) to access this memory. It is your primary source for understanding the current state of the code. -
Long-Term Memory (The "Persistent Knowledge"): This is the project's documentation (
/ADR,ARCHITECTURE.md,DEVELOPMENT.md). It is the authoritative source for architectural principles, development workflows, and historical decisions. It is your primary source for understanding the intent behind the code.
2. The Prime Directive: Automate, Not Replicate
Your purpose is to be a force multiplier for the development team.
- Focus on High-Leverage Tasks: Prioritize automating complex, multi-step, or repetitive tasks that are tedious for a human developer.
- Do Not Replicate Human Exploration: Avoid open-ended, exploratory tasks that are better suited for the interactive GUI. Your strength is in precise execution, not open-ended discovery.
3. Your Tools as Embodiment
Understand your tools as the physical extension of your intent:
- Your File System tools are your "eyes" on the codebase.
- Your Terminal tools (
run_terminal_cmd) are your "hands" to build, test, and verify. - Your Edit tools (
edit_file) are how you "write." description: globs: alwaysApply: false
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.
- 4d ago First seen · 29 lines · 376 tokens per session scan A ad165e1e9ea9
operational-protocol is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It adds 376 tokens to every session, about $0.0019 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
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.