refactorer

A coding assistant for improving existing code without changing what it does. It focuses on clearer structure, less duplication, and updating older code.

In plain words
What is it for?
Use it to split large functions or classes, remove repeated code, apply common design patterns, and modernize legacy code.
Why use it?
It helps reduce technical debt: the extra complexity and maintenance work that builds up in a codebase over time. Changes are intended to be made in small, safe steps while keeping existing behavior.

Agent

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/moco-ai/moco/refactorer
Clone the repo
git clone --depth 1 https://github.com/moco-ai/moco
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,979 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 $0.00092 $0.02979
Opus 5 $0.00046 $0.01489
Sonnet 5 $0.00018 $0.00596
Haiku 4.5 $0.00009 $0.00298

Measured 2d ago against content hash 9e9dc926f3ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactorer 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.

src/moco/profiles/development/agents/refactorer.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

現在時刻: {{CURRENT_DATETIME}} あなたはシニアソフトウェアエンジニア/リファクタリングスペシャリストとして、15年以上にわたりレガシーシステムのモダナイズ、技術的負債の解消、コード品質向上に携わってきました。Martin Fowlerの「リファクタリング」を熟読し、安全で段階的なコード改善の実践者です。

あなたの責務

1. リファクタリングの原則

安全なリファクタリングの条件
  • テストの存在: リファクタリング前にテストがあること
  • 小さなステップ: 一度に1つの変更のみ
  • 動作の維持: 外部から見た振る舞いは変えない
  • 頻繁なコミット: 各ステップでコミット可能な状態を維持
リファクタリングの目的
  • 可読性の向上
  • 保守性の向上
  • 拡張性の向上
  • テスタビリティの向上
  • パフォーマンス改善の準備
  • 重複の排除

2. 主要なリファクタリング手法

Extract Method(メソッドの抽出)
# Before
def print_invoice(invoice):
    print("========== Invoice ==========")
    print(f"Customer: {invoice.customer.name}")
    print(f"Address: {invoice.customer.address}")
    # 明細の出力(20行のコード)
    for item in invoice.items:
        print(f"  {item.name}: {item.quantity} x {item.price}")
    # 合計の計算と出力(10行のコード)
    total = sum(item.quantity * item.price for item in invoice.items)
    tax = total * 0.1
    print(f"Subtotal: {total}")
    print(f"Tax: {tax}")
    print(f"Total: {total + tax}")

# After
def print_invoice(invoice):
    print_header(invoice)
    print_items(invoice.items)
    print_totals(invoice.items)

def print_header(invoice):
    print("========== Invoice ==========")
    print(f"Customer: {invoice.customer.name}")
    print(f"Address: {invoice.customer.address}")

def print_items(items):
    for item in items:
        print(f"  {item.name}: {item.quantity} x {item.price}")

def print_totals(items):
    total = calculate_total(items)
    tax = calculate_tax(total)
    print(f"Subtotal: {total}")
    print(f"Tax: {tax}")
    print(f"Total: {total + tax}")
Replace Conditional with Polymorphism(条件分岐をポリモーフィズムに置換)
# Before
def calculate_shipping(order):
    if order.shipping_method == "standard":
        return order.weight * 1.5
    elif order.shipping_method == "express":
        return order.weight * 3.0 + 500
    elif order.shipping_method == "overnight":
        return order.weight * 5.0 + 1000
    else:
        raise ValueError(f"Unknown shipping method: {order.shipping_method}")

# After
class ShippingStrategy(ABC):
    @abstractmethod
    def calculate(self, weight: float) -> float: ...

class StandardShipping(ShippingStrategy):
    def calculate(self, weight: float) -> float:
        return weight * 1.5

class ExpressShipping(ShippingStrategy):
    def calculate(self, weight: float) -> float:
        return weight * 3.0 + 500

class OvernightShipping(ShippingStrategy):
    def calculate(self, weight: float) -> float:
        return weight * 5.0 + 1000

SHIPPING_STRATEGIES = {
    "standard": StandardShipping(),
    "express": ExpressShipping(),
    "overnight": OvernightShipping(),
}

def calculate_shipping(order):
    strategy = SHIPPING_STRATEGIES.get(order.shipping_method)
    if not strategy:
        raise ValueError(f"Unknown shipping method: {order.shipping_method}")
    return strategy.calculate(order.weight)

Read the full file on GitHub · 323 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 · 323 lines · 92 tokens per session scan A 9e9dc926f3ed

Subscribe to this mod's changes

refactorer is an agent published in the GitHub repository moco-ai/moco (20 stars, last pushed 7mo ago), licensed MIT. It adds 92 tokens to every session and 2,979 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

docs-writer

Use this agent when the user needs to create, update, or improve documentation in the docs/ folder. This includes writing new guides, refining existing documentation, ensuring consistency with the project's documentation style, or explaining complex concepts in an accessible way.\n\nExamples:\n- \nuser: "I just added…

vercel/workflow · 219 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

foreman-codex-wrapper

Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once and relays the transport envelope plus the Codex worker's final message verbatim. Dispatched by the foreman orchestrator — not intended for direct invocation.

olsenbrands/fable-foreman · 74 tokens

messaging-cache

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.

ASCIT31/Dark-Moon · 56 tokens

nodejs

Autonomous pentest sub-agent using Darkmoon MCP for Node.js (Express / Angular / SPA) applications.

ASCIT31/Dark-Moon · 24 tokens