03-refactor

A set of instructions for cleaning up, reorganising, or improving existing code while keeping its behaviour unchanged.

In plain words
What is it for?
Use it to rename code, extract reusable functions, reduce duplication, simplify conditions, improve types, and optimise performance.
Why use it?
It gives refactoring work a consistent process, including small changes, tests, and explanations.

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/jonafrank/cursor-multi-model-config/03-refactor
Clone the repo
git clone --depth 1 https://github.com/jonafrank/cursor-multi-model-config

Made for: Cursor.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 $0.00012 $0.00358
Opus 5 $0.00006 $0.00179
Sonnet 5 $0.00002 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 2d ago against content hash ff983a9c692e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03-refactor 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/03-refactor.mdc · 53 lines

What it actually says

Refactor Mode

This rule activates for code refactoring and improvement tasks.

When This Applies

  • Cleaning up messy code
  • Improving code organization
  • Renaming variables/functions for clarity
  • Extracting reusable components
  • Applying design patterns
  • Optimizing performance

Model Recommendation

Check .cursor/model-profiles/current-profile.json for the refactor model.

Typical models for refactoring:

  • gpt-5.2 (completeness profile)
  • gpt-5.1-codex-high (default profile)
  • composer-1 (cost_minimized/fallback profile)

Refactoring Guidelines

  1. Preserve behavior: Refactoring should not change functionality
  2. Small steps: Make incremental changes, not massive rewrites
  3. Test coverage: Ensure tests exist before refactoring
  4. Explain changes: Document what changed and why
  5. Follow conventions: Match existing codebase style

Refactoring Patterns

  • Extract Method: Pull repeated code into a function
  • Rename: Use clear, descriptive names
  • Simplify Conditionals: Reduce nesting, use early returns
  • Remove Duplication: DRY principle
  • Improve Types: Add/strengthen type annotations

Output Format

For refactoring tasks:

  1. Current State: What needs improvement
  2. Proposed Changes: What will change
  3. Benefits: Why this improves the code
  4. Code: The refactored implementation
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 · 53 lines · 12 tokens per session scan A ff983a9c692e

Subscribe to this mod's changes

03-refactor is a cursor rule published in the GitHub repository jonafrank/cursor-multi-model-config (5 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 358 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.