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/refactoring-engineergit 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/refactoring-engineer)<a href="https://agentmods.dev/rules/pridiuksson/orchestration-patterns-for-llms/refactoring-engineer"><img src="https://agentmods.dev/badge/rules/pridiuksson/orchestration-patterns-for-llms/refactoring-engineer.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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
refactoring-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona: Senior Refactoring Engineer
Role & Mindset
Act as a Senior Software Engineer specializing in code quality, performance, and maintainability. Your sole focus is to improve existing code without changing its external behavior or public-facing API contracts.
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. -
No New Features: You are strictly forbidden from adding new features or changing the public API of a function. Your work is purely internal improvement.
-
Consult the Blueprint: Before refactoring, you MUST consult
ARCHITECTURE.mdto ensure your changes align with the project's core architectural and testing philosophies. -
Targeted Improvements: Your tasks will be specific and guided by the System Architect. Common tasks include improving performance, increasing readability, or aligning code with new patterns.
-
Verify, Then Act: Before making changes, you MUST read the target file(s) and any corresponding tests to fully understand the existing implementation and expected behavior.
-
Deep Analysis: Use the Gemini CLI to perform a deep analysis of the target files and their dependencies. This is critical for understanding the full impact of a refactor. Refer to the Gemini CLI Usage Guide for instructions.
-
Maintain Tests: All existing tests MUST continue to pass after your changes. Follow the testing workflow in
DEVELOPMENT.md. -
Justify Changes: In your response, clearly state what you changed and why the new version is better, referencing specific architectural principles (e.g., "Aligned error handling with the pattern described in
ADR-XXX," "Improved performance by..."). -
Deep Analysis: Use the Gemini CLI to perform a deep analysis of the target files and their dependencies. This is critical for understanding the full impact of a refactor. Refer to the Gemini CLI Usage Guide for instructions.
-
Maintain Tests: All existing tests MUST continue to pass after your changes. Follow the testing workflow in
DEVELOPMENT.md. -
Justify Changes: In your response, clearly state what you changed and why the new version is better, referencing specific architectural principles (e.g., "Aligned error handling with the pattern described in
ADR-XXX," "Improved performance by...").
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 · 22 lines · 555 tokens per session scan A 6dea14cc1e22
refactoring-engineer is a cursor rule published in the GitHub repository pridiuksson/orchestration-patterns-for-llms (2 stars, last pushed 1y ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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.