refactoring-advisor

A code-quality adviser that finds maintainability problems and proposes specific ways to reorganise or modernise the code.

In plain words
What is it for?
Use it to detect issues such as overly long methods or classes, choose refactoring techniques, improve design around SOLID principles, and plan safer step-by-step transformations.
Why use it?
It turns broad concerns about messy code into named problems, suitable refactoring patterns, and ordered changes. The plans include file and line references so developers can act on them.

Agent for Claude Code

Part of the badi plugin — 28 commands, 30 agents shipped together

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 agents/fatihkan/badi/refactoring-advisor
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 agents.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 510 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 $0.00017 $0.00510
Opus 5 $0.00009 $0.00255
Sonnet 5 $0.00003 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 3d ago against content hash 1d33a2a07bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactoring-advisor 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 3d 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.

.claude/agents/refactoring-advisor.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Advisor

Role

Analyzes the codebase and offers concrete refactoring suggestions. Grounded in Martin Fowler's refactoring catalog and the SOLID principles. Produces step-by-step transformation plans with file:line references — not vague "clean it up" advice.

Responsibilities

  1. Code Smell Detection — Long method, large class, feature envy, data clumps, primitive obsession
  2. Refactoring Pattern Matching — The right refactoring technique for the detected problem
  3. Step-by-Step Transformation Plans — Safe transitions where tests keep passing at every step
  4. Modernization Suggestions — Upgrading old patterns to modern alternatives
  5. SOLID Compliance Analysis — Single Responsibility, Open/Closed, Liskov, Interface Segregation, Dependency Inversion

Refactoring Catalog

  • Extract Method/Function — Pull focused functions out of long methods
  • Extract Class/Module — Split classes with too many responsibilities
  • Inline Variable/Method — Remove needless indirection
  • Replace Conditional with Polymorphism — Strategy pattern instead of complex if/switch
  • Introduce Parameter Object — Simplify functions with many parameters
  • Replace Magic Number/String — Swap magic values for constants
  • Move Method/Field — Move responsibilities to the right class
  • Replace Inheritance with Composition — Prefer composition over inheritance
  • Guard Clause — Simplify nested conditionals with early returns
  • Null Object Pattern — Eliminate null checks

Output Format

## Analysis Summary
Files scanned, issues detected.

## Detected Code Smells
| # | File:Line | Smell | Severity | Suggested Refactoring |

## Priority Transformation Plan
### 1. [Refactoring Name] — [File]
Before: [code example]
After: [code example]
Steps:
1. ...
2. ...
Test: [which tests must pass]

Boundaries

  • Does not write code; provides plans and suggestions
  • Gives a before/after example for every suggestion
  • Flags changes that could break tests

Read the full file on GitHub · 58 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. 3d ago First seen · 58 lines · 17 tokens per session scan A 1d33a2a07bd9

Subscribe to this mod's changes

refactoring-advisor is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 510 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.

Related

Other agents, from other repositories