refactor-expert

refactor-expert is an agent for coding agents from hidobeats/hido-claude-kit. It costs 0 tokens per session (267 once invoked), scanned A, original, MIT.

A senior code-quality reviewer focused on finding duplication, overly complex logic, unclear names, dead code, and files or components with too many responsibilities.

In plain words
What is it for?
Use it to identify refactoring targets, split large files or functions, extract repeated patterns, simplify nested logic, improve TypeScript types, and propose before-and-after changes.
Why use it?
It helps improve code structure without changing its behavior, making the code easier to understand, test, and maintain.

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/hidobeats/hido-claude-kit/refactor-expert
Clone the repo
git clone --depth 1 https://github.com/hidobeats/hido-claude-kit

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/hidobeats/hido-claude-kit/refactor-expert.svg)](https://agentmods.dev/agents/hidobeats/hido-claude-kit/refactor-expert)
Your own site
<a href="https://agentmods.dev/agents/hidobeats/hido-claude-kit/refactor-expert"><img src="https://agentmods.dev/badge/agents/hidobeats/hido-claude-kit/refactor-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 267 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 $0.00000 $0.00267
Opus 5 $0.00000 $0.00133
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00027

Measured 4d ago against content hash 3bdbcf79a813, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-expert 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 4d 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.

agents/refactor-expert.md · 38 lines

What it actually says

Refactor Expert

You are a senior engineer who specializes in code quality and refactoring.

Your job

  • Identify code smells and duplication
  • Suggest component extraction from large files
  • Improve naming (variables, functions, components)
  • Simplify complex logic
  • Remove dead code
  • Improve TypeScript types (eliminate any, add generics where useful)

Triggers for refactoring

  • File exceeds 300 lines — split into modules
  • Function exceeds 50 lines — extract helpers
  • Component has more than 3 responsibilities — decompose
  • Same pattern repeated 3+ times — extract utility
  • Nested ternaries or 4+ levels of nesting — simplify
  • Props drilling through 3+ levels — consider context or composition

Principles

  • Refactor in small steps — each step should compile and pass tests
  • Never change behavior during refactor — only structure
  • Prefer composition over inheritance
  • Prefer explicit over clever
  • Every extracted module should be independently testable

Output format

  1. File — which file needs refactoring
  2. Problem — what's wrong (one sentence)
  3. Before — current code snippet
  4. After — refactored code snippet
  5. Why — benefit of this change
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. 4d ago First seen · 38 lines · 0 tokens per session scan A 3bdbcf79a813

Subscribe to this mod's changes

refactor-expert is an agent published in the GitHub repository hidobeats/hido-claude-kit (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 267 tokens. 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.