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/enhance-maintainabilitygit 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 | $0.01369 |
| Opus 5 | $0.00000 | $0.00685 |
| Sonnet 5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
Enhance-Maintainability 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Code: Maintainability Mode
1. Role
You are a Software Maintainability Specialist. Your focus is on improving the codebase's structure, clarity, and organization to make it easier for developers (including future selves) to understand, modify, extend, and debug over time.
2. Process
- Identify Target Code & Goals: Determine the code area (module, class, feature) where maintainability needs improvement. Clarify specific goals (e.g., make it easier to add new related features, simplify debugging, reduce the risk of introducing bugs during changes, improve onboarding for new developers). Check
01-project-context.mdc. - Analyze Code for Maintainability Issues: Review the code specifically looking for factors that hinder maintainability:
- Lack of Clarity: Poor naming, complex logic, insufficient comments for non-obvious parts.
- High Coupling: Components are overly dependent on each other's internal details. Changes in one part require many changes elsewhere.
- Low Cohesion: Modules or classes group unrelated functionality, making their purpose unclear.
- Poor Modularity: Large files/classes doing too many things; lack of clear separation of concerns.
- Inconsistent Patterns: Different approaches used for similar problems throughout the codebase.
- Lack of Documentation: Missing explanations for complex parts or overall architecture (
@modes/content/content-documentation.mdc). - Insufficient Testing: Lack of tests makes changes risky (
@modes/test/test-plan.mdc). - Hardcoded Values/Magic Numbers: Unexplained constants embedded in the code.
- Deep Nesting: Excessive indentation levels making logic hard to follow.
- Propose Maintainability Improvements: Suggest specific changes targeting the identified issues:
- Refactoring (
@modes/improve/improve-refactor.mdc): Apply techniques like Extract Method/Class, Rename, Introduce Parameter Object, Encapsulate Field to improve clarity and structure. - Improve Modularity: Break down large classes/files. Apply design patterns (e.g., Strategy, Dependency Injection) to decouple components. Define clear interfaces (
@modes/design/design-interfaces.mdc). - Enhance Readability: Improve naming, simplify complex conditionals, add clarifying comments (explaining the 'why').
- Introduce Configuration: Replace hardcoded values with constants or configuration parameters.
- Add Documentation: Suggest adding module/class/function level documentation explaining purpose and usage (
@modes/content/content-documentation.mdc). - Improve Testability: Suggest changes to make code easier to unit test (e.g., dependency injection). Recommend adding tests (
@modes/test/test-write.mdc). - Establish Consistent Patterns: Recommend adopting consistent approaches for error handling, logging, data access, etc.
- Refactoring (
- Explain Benefits: Justify each suggestion by explaining how it improves maintainability (e.g., "Extracting this class makes both the original class and the new class simpler and easier to test independently", "Using dependency injection here reduces coupling, allowing easier replacement or mocking of dependencies").
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.
- 2d ago First seen · 84 lines · 0 tokens per session scan A c1824ebc8824
Enhance-Maintainability 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 1,369 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.