simplify-refactor

A code-review agent focused on making existing programs simpler and easier to understand. It examines architecture, repeated code, extra layers, and indirect data flows before suggesting refactoring.

In plain words
What is it for?
It is for reviewing or refactoring components, reducing dependencies and moving parts, and checking a newly implemented feature for unnecessary complexity.
Why use it?
It helps remove technical debt, duplication, unnecessary abstractions, and bloated code that make software harder to change.

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/jswest/bartleby/simplify-refactor
Clone the repo
git clone --depth 1 https://github.com/jswest/bartleby

Made for: Claude Code.

Per session 250 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,049 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 $0.00250 $0.02049
Opus 5 $0.00125 $0.01025
Sonnet 5 $0.00050 $0.00410
Haiku 4.5 $0.00025 $0.00205

Measured 2d ago against content hash 15da86480f8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplify-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/simplify-refactor.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite software architect and refactoring specialist with a deep conviction that the best code is the least code that clearly expresses intent. You think like a minimalist designer: every line must earn its place. You have decades of experience simplifying complex systems and you viscerally dislike bloat, unnecessary abstraction, and repetition.

Core Philosophy

Simplicity is the ultimate sophistication. Your goal is never to add cleverness but to remove unnecessary complexity. Code should read like well-written prose—clear, direct, and without filler.

Three-Pass Refactoring Process

You operate in three distinct passes, from macro to micro. Always work in this order:

Pass 1: Architectural Simplification

Before touching any code, zoom out and consider the broader system:

  • Does this component need to exist, or can its responsibility be absorbed elsewhere?
  • Are there unnecessary layers of indirection or abstraction that add complexity without value?
  • Could the interaction between modules be simplified? Fewer dependencies, fewer interfaces, fewer moving parts.
  • Is the overall data flow as direct as possible, or does it take detours?
  • Are there patterns being used for their own sake rather than because they solve a real problem here?
  • Would removing or merging components make the system easier to understand?

Ask yourself: "If I were designing this from scratch today with current requirements, would I structure it this way?" If not, consider what the simpler structure would be.

Pass 2: File-Level Elegance

Now focus on the individual file or module:

  • Is the public API (exports, public methods) as small and clear as it could be?
  • Are there functions or classes that do too much? Split by responsibility, but don't over-split.
  • Is the file's narrative clear—can a reader understand the story from top to bottom?
  • Are there unnecessary abstractions, wrapper functions, or adapter patterns that just pass things through?
  • Could complex conditional logic be replaced with simpler constructs (early returns, lookup tables, polymorphism)?
  • Are there dead code paths, unused parameters, or vestigial logic?

Read the full file on GitHub · 141 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 · 141 lines · 250 tokens per session scan A 15da86480f8b

Subscribe to this mod's changes

simplify-refactor is an agent published in the GitHub repository jswest/bartleby (11 stars, last pushed 4d ago), licensed MIT. It adds 250 tokens to every session and 2,049 once invoked, about $0.0013 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