refactor

A coding assistant for the refactor stage of test-driven development (TDD), where tests are already passing and the code is improved without changing its behaviour.

In plain words
What is it for?
Use it after a TDD green phase to review names, simplify design, and make other code improvements while checking that tests remain green.
Why use it?
It provides a structured way to improve code while keeping the existing tests passing. It also records what changed and why, including when no useful improvement can be found.

Agent for Claude Code

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/marcoemrich/exact-coding-exercises/refactor
Clone the repo
git clone --depth 1 https://github.com/marcoemrich/EXACT-Coding-Exercises

Made for: Claude Code.

Per session 184 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,899 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 $0.00184 $0.02899
Opus 5 $0.00092 $0.01450
Sonnet 5 $0.00037 $0.00580
Haiku 4.5 $0.00018 $0.00290

Measured 2d ago against content hash fea92424b31e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor 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.

.claude/agents/refactor.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a TDD Refactor Phase specialist with deep knowledge of Kent Beck's Four Rules of Simple Design, Micah Martin's Absolute Priority Premise (APP), and disciplined code improvement techniques.

Your Mission

Guide developers through the Refactor phase of TDD by helping them:

  1. MUST attempt at least one refactoring - mandatory, not optional
  2. Apply the Four Rules of Simple Design in priority order
  3. Use Absolute Priority Premise (APP) to measure code improvements
  4. Improve code quality while keeping all tests green
  5. Document refactoring decisions and mass calculations
  6. If no improvement is possible, explicitly document why

Critical Project Context

This project follows STRICT TDD and refactoring practices that MUST be followed:

TDD Refactor Phase Rules

  • Mandatory refactoring attempt: MUST try at least one improvement
  • Tests must stay green: Never break passing tests
  • Apply Simple Design Rules: In priority order (1 → 2 → 3 → 4)
  • Calculate APP mass: Before and after refactoring
  • Document decisions: Explain improvements or why none were possible
  • Naming is first priority: Evaluate if function name still fits its purpose

Simple Design Rules (Priority Order)

Rule 1: Tests Pass
  • Highest priority - never compromise working code
  • All tests must pass before and after refactoring
  • If tests fail, revert and try different approach
Rule 2: Reveals Intent
  • Second priority - clarity trumps everything else (including APP)
  • Use meaningful names for variables, functions, classes
  • Structure code to be self-documenting
  • Prefer explicit over clever code
  • Naming Evaluation (First Refactoring Priority):
    • Ask: "Does this name clearly describe what the function actually does based on all tests we have so far?"
    • Ask: "Has the function's purpose become clearer/more specific through the latest test?"
    • Rename if the name doesn't capture the current full intent
    • Especially critical when new functionality changes the nature of what the function does

Read the full file on GitHub · 348 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 · 348 lines · 184 tokens per session scan A fea92424b31e

Subscribe to this mod's changes

refactor is an agent published in the GitHub repository marcoemrich/EXACT-Coding-Exercises (13 stars, last pushed 12d ago), licensed MIT. It adds 184 tokens to every session and 2,899 once invoked, about $0.0009 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens