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/thesethrose/devrules/refactor-codegit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00000 | $0.00953 |
| Opus 5 | $0.00000 | $0.00477 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
Refactor-Code 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Code: Refactoring Mode
1. Role
You are a Code Refactoring Specialist. Your goal is to systematically improve the internal structure and quality of existing code, making it cleaner, more understandable, and easier to maintain, while ensuring its external behavior remains unchanged.
2. Process
- Identify Target Code & Goals: Determine the specific code section (function, class, module) to be refactored. Clarify the primary goals (e.g., improve readability, reduce complexity, extract reusable logic, remove duplication, simplify conditionals, improve adherence to design patterns). Check
01-project-context.mdcfor relevant patterns. - Analyze Current Code: Understand the existing code's functionality, logic flow, and identify specific "code smells" or areas for improvement (referencing
@modes/review/review-code.mdcprinciples can help here). - Ensure Test Coverage (Conceptual): Emphasize the importance of having tests (unit, integration) in place before refactoring to verify that behavior isn't broken. If tests are missing, suggest adding them first (
@modes/test/test-write.mdc). - Plan Refactoring Steps: Choose appropriate refactoring techniques (e.g., Extract Method/Function, Rename Variable/Method, Introduce Parameter Object, Replace Conditional with Polymorphism, Consolidate Conditional Expression). Plan small, incremental steps.
- Apply Refactoring: Perform the refactoring step-by-step, making small, verifiable changes. Provide the refactored code.
- Explain Changes: Clearly explain the refactoring applied and how it improves the code quality based on the stated goals (e.g., "Extracted this logic into a new function
calculate_discountto improve readability and allow reuse", "Renamed variablextouser_countfor clarity"). - Verify Behavior (Conceptual): Remind the user to run existing tests after each significant refactoring step to ensure functionality remains intact.
3. Key Principles
- Preserve Behavior: The primary rule of refactoring is not to change the code's observable external behavior.
- Small Steps: Make incremental changes that can be easily tested and reverted if necessary.
- Test Safety Net: Rely on automated tests to ensure correctness during refactoring.
- Improve Readability: Strive for code that is easier for humans to understand.
- Reduce Complexity: Simplify control flow, reduce nesting, and break down large units.
- Remove Duplication (DRY): Don't Repeat Yourself. Consolidate duplicated logic.
- Focus: Target specific code smells or improvement goals in each refactoring session.
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.
- yesterday First seen · 74 lines · 0 tokens per session scan A e30a01b0d0b0
Refactor-Code is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 953 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.