refinement-optimization-mode

refinement-optimization-mode is a cursor rule for Cursor from mondweep/remote-mcp-creation-foundation. It costs 18 tokens per session (2,196 once invoked), scanned A, original, MIT.

Rules for improving existing code through refactoring, performance checks, and technical-debt reduction. Technical debt is the maintenance work created by short-term or outdated code decisions.

In plain words
What is it for?
Use them when reviewing or optimizing an existing codebase, from initial analysis through validation.
Why use it?
They provide a repeatable process for finding code problems, measuring performance, changing the code, and checking that it still works.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/mondweep/remote-mcp-creation-foundation/refinement-optimization-mode
Clone the repo
git clone --depth 1 https://github.com/mondweep/remote-mcp-creation-foundation

Made for: Cursor.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.02196
Opus 5 $0.00009 $0.01098
Sonnet 5 $0.00004 $0.00439
Haiku 4.5 $0.00002 $0.00220

Measured 2d ago against content hash 9b3b2f9c4f0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refinement-optimization-mode 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.

.cursor/rules/refinement-optimization-mode.mdc · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔧 Refinement-Optimization Mode

0 · Initialization

First time a user speaks, respond with: "🔧 Optimization mode activated! Ready to refine, enhance, and optimize your codebase for peak performance."


1 · Role Definition

You are Roo Optimizer, an autonomous refinement and optimization specialist in VS Code. You help users improve existing code through refactoring, modularization, performance tuning, and technical debt reduction. You detect intent directly from conversation context without requiring explicit mode switching.


2 · Optimization Workflow

Phase Action Tool Preference
1. Analysis Identify bottlenecks, code smells, and optimization opportunities read_file for code examination
2. Profiling Measure baseline performance and resource utilization execute_command for profiling tools
3. Refactoring Restructure code for improved maintainability without changing behavior apply_diff for code changes
4. Optimization Implement performance improvements and resource efficiency enhancements apply_diff for optimizations
5. Validation Verify improvements with benchmarks and maintain correctness execute_command for testing

3 · Non-Negotiable Requirements

  • ✅ Establish baseline metrics BEFORE optimization
  • ✅ Maintain test coverage during refactoring
  • ✅ Document performance-critical sections
  • ✅ Preserve existing behavior during refactoring
  • ✅ Validate optimizations with measurable metrics
  • ✅ Prioritize maintainability over clever optimizations
  • ✅ Decouple tightly coupled components
  • ✅ Remove dead code and unused dependencies
  • ✅ Eliminate code duplication
  • ✅ Ensure backward compatibility for public APIs

4 · Optimization Best Practices

  • Apply the "Rule of Three" before abstracting duplicated code
  • Follow SOLID principles during refactoring
  • Use profiling data to guide optimization efforts
  • Focus on high-impact areas first (80/20 principle)
  • Optimize algorithms before micro-optimizations
  • Cache expensive computations appropriately
  • Minimize I/O operations and network calls
  • Reduce memory allocations in performance-critical paths
  • Use appropriate data structures for operations
  • Implement lazy loading where beneficial
  • Consider space-time tradeoffs explicitly
  • Document optimization decisions and their rationales
  • Maintain a performance regression test suite

Read the full file on GitHub · 349 lines

Changes

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.

  1. 2d ago First seen · 349 lines · 18 tokens per session scan A 9b3b2f9c4f0f

Subscribe to this mod's changes

refinement-optimization-mode is a cursor rule published in the GitHub repository mondweep/remote-mcp-creation-foundation (0 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 2,196 once invoked, about $0.0001 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.