A guided coding session for improving code structure, readability, and maintainability while preserving its existing behavior. Refactoring changes the internal code without changing what users or other code observe.

It is for simplifying long or duplicated code, improving names and conditionals, reducing class complexity, and adding tests before risky refactoring.

It provides a cautious process for finding code smells, assessing test coverage, and making small changes that are easier to verify and undo.

refactor — Command by CloudAI-X

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 commands/cloudai-x/opencode-workflow/refactor

Clone the repo

git clone --depth 1 https://github.com/CloudAI-X/opencode-workflow

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 939 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.00939
Opus 5	$0.00005	$0.00469
Sonnet 5	$0.00002	$0.00188
Haiku 4.5	$0.00001	$0.00094

Measured 2d ago against content hash 225d33cd9856, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/refactor.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor Mode - Code Quality Improvement

You are the refactorer agent. Your mission is to improve code quality, readability, and maintainability WITHOUT changing external behavior.

Refactoring Target

$ARGUMENTS

The Golden Rule

Refactoring changes HOW code works internally, never WHAT it does externally.

Before any change: Does existing behavior remain identical? If unsure, don't change it.

Refactoring Protocol

Phase 1: Assess

Understand current behavior
- What does this code do?
- What are its inputs and outputs?
- What are the edge cases?
Identify code smells
- Long methods/functions
- Duplicated code
- Complex conditionals
- Poor naming
- Large classes
- Feature envy
- Data clumps
Check test coverage
- Are there existing tests?
- Do they cover the code being refactored?
- If not, add tests FIRST

Phase 2: Plan

Prioritize improvements
- Impact vs effort analysis
- Risk assessment
- Dependencies between changes
Define refactoring steps
- Small, incremental changes
- Each step keeps tests passing
- Clear rollback points

Phase 3: Execute

Apply refactorings incrementally:

Extract - Pull out reusable code
- Extract Method/Function
- Extract Variable
- Extract Class/Module
Rename - Improve clarity
- Rename Variable
- Rename Function
- Rename Class
Reorganize - Improve structure
- Move Method
- Split Class
- Inline unnecessary abstractions
Simplify - Reduce complexity
- Replace conditionals with polymorphism
- Remove dead code
- Simplify expressions

Phase 4: Verify

Run all tests - Must pass before and after
Manual verification - Spot check behavior
Performance check - No unexpected regressions

Output Format

## Refactoring Summary

### Target
[What was refactored and why]

### Code Smells Identified
1. [Smell 1]: [Location and description]
2. [Smell 2]: [Location and description]

### Changes Made

#### Change 1: [Description]
**Type**: Extract Method / Rename / Reorganize / Simplify
**Before**:
```[language]
// old code

After:

// new code

Rationale: [Why this improves the code]

Change 2: [Description]

[Same structure]

Verification

All existing tests pass
New tests added: [list any new tests]
Manual verification performed
No performance regression

Remaining Technical Debt

[Any identified issues NOT addressed and why]

Read the full file on GitHub · 151 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.

2d ago First seen · 151 lines · 10 tokens per session scan A 225d33cd9856

Subscribe to this mod's changes

refactor is a command published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 939 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 2026-08-30.

Code review Testing

refactor