refactor-code

refactor-code is an agent for coding agents from juyamagu/azure-updates-mcp-server. It costs 19 tokens per session (260 once invoked), scanned A, original, MIT.

An agent for improving existing code while preserving what the code does from the outside. It focuses on clearer structure, names, documentation, consistent style, less duplication, and performance.

In plain words
What is it for?
Refactoring code from the current changes, updating related documentation, running tests, and summarising the resulting edits.
Why use it?
It helps clean up changed code without turning the refactoring into a behavior change, and asks for tests to catch regressions.

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/juyamagu/azure-updates-mcp-server/refactor-code
Clone the repo
git clone --depth 1 https://github.com/juyamagu/azure-updates-mcp-server

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for refactor-code

README.md
[![agentmods](https://agentmods.dev/badge/agents/juyamagu/azure-updates-mcp-server/refactor-code.svg)](https://agentmods.dev/agents/juyamagu/azure-updates-mcp-server/refactor-code)
Your own site
<a href="https://agentmods.dev/agents/juyamagu/azure-updates-mcp-server/refactor-code"><img src="https://agentmods.dev/badge/agents/juyamagu/azure-updates-mcp-server/refactor-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 260 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 $0.00019 $0.00260
Opus 5 $0.00010 $0.00130
Sonnet 5 $0.00004 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 2d ago against content hash 35d11c2f8866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-code 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.

.github/agents/refactor-code.agent.md · 23 lines

What it actually says

Refactor the code that has been changed in the current context (e.g. git diff) to enhance its quality. Focus on improving:

  • Readability: Use clear variable and function names, add comments where necessary, and structure the code logically.
  • Maintainability: Break down large functions into smaller ones, reduce code duplication, and adhere to design patterns.
  • Consistency: Ensure coding style is uniform across the codebase, following established conventions. Documents should also be updated to reflect code changes.

Steps

  1. Analyze the provided code changes to understand their purpose and functionality.
  2. Identify areas for improvement in readability, maintainability, and performance.
  3. Refactor the code while ensuring that its external behavior remains unchanged.
  4. Run tests to verify that the refactored code works as intended.
  5. If failures or any issues arise, go back to step 3 and iterate until the code is stable. Otherwise, proceed to step 6.
  6. Provide a summary of the changes made during the refactoring process.

Constitution

Refer to .specify/memory/constitution.md for the coding standards and principles to follow during the refactoring process.

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 · 23 lines · 19 tokens per session scan A 35d11c2f8866

Subscribe to this mod's changes

refactor-code is an agent published in the GitHub repository juyamagu/azure-updates-mcp-server (0 stars, last pushed 8mo ago), licensed MIT. It adds 19 tokens to every session and 260 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.