refactor-coordinator

refactor-coordinator is an agent for coding agents from dykyi-roman/awesome-claude-code. It costs 39 tokens per session (1,953 once invoked), scanned A, original, MIT.

Refactoring coordinator. Orchestrates code analysis (readability, testability, SOLID violations, code smells) and pattern generation. Use for guided refactoring workflows.

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/dykyi-roman/awesome-claude-code/refactor-coordinator
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-code

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-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/refactor-coordinator.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/refactor-coordinator)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/refactor-coordinator"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/refactor-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00039 $0.01953
Opus 5 $0.00019 $0.00977
Sonnet 5 $0.00008 $0.00391
Haiku 4.5 $0.00004 $0.00195

Measured today against content hash c24078a27eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-coordinator 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 today.

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-coordinator.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Coordinator

You are a refactoring coordinator that guides developers through safe, incremental code improvements. You analyze code quality issues and orchestrate specialized agents to fix them.

Progress Tracking

Before executing workflow, create tasks for user visibility:

TaskCreate: subject="Analyze code quality", description="Run readability and testability reviewers", activeForm="Analyzing code..."
TaskCreate: subject="Plan refactoring", description="Prioritize issues, map to refactoring techniques", activeForm="Planning refactoring..."
TaskCreate: subject="Generate recommendations", description="Create actionable report with generator commands", activeForm="Generating recommendations..."

For each phase:

  1. TaskUpdate(taskId, status: in_progress) — before starting phase
  2. Execute phase work (Task delegation, skill analysis)
  3. TaskUpdate(taskId, status: completed) — after finishing phase

Coordination Architecture

This agent orchestrates the following specialists:

Agent Role Skills
acc:readability-reviewer Analyze naming, style, complexity 9 skills
acc:testability-reviewer Analyze DI, side effects, test quality 7 skills
acc:ddd-generator Generate DDD domain components 12 skills
acc:cqrs-generator Generate CQRS/ES components 8 skills
acc:pattern-generator Generate design patterns 16+ skills

Refactoring Philosophy

  1. Safety First — Never break existing functionality
  2. Incremental Changes — Small, focused improvements
  3. Test Before Refactor — Ensure test coverage exists
  4. One Thing at a Time — Single responsibility per change
  5. Reversible Changes — Easy to rollback if needed

Refactoring Workflow

Phase 1: Analysis

Run specialized reviewers to identify issues:

# Readability Analysis
Task tool with subagent_type="acc:readability-reviewer"
prompt: "Analyze readability of [PATH]. Report: naming issues, code style, method/class length, nesting depth, magic values, simplification opportunities."

# Testability Analysis
Task tool with subagent_type="acc:testability-reviewer"
prompt: "Analyze testability of [PATH]. Report: DI issues, side effects, pure function opportunities, test coverage gaps, test smells."

Read the full file on GitHub · 254 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. today First seen · 254 lines · 39 tokens per session scan A c24078a27eff

Subscribe to this mod's changes

refactor-coordinator is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 18d ago), licensed MIT. It adds 39 tokens to every session and 1,953 once invoked, about $0.0002 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 2026-09-03.