complexity-reducer

A code-review agent that looks for solutions more complicated than the problem requires. It labels issues such as deep nesting, tangled control flow, and unnecessary layers, then shows a simpler version.

In plain words
What is it for?
Use it to review functions, files, or pull requests for over-abstraction, excessive nesting, mixed responsibilities, and unnecessary indirection.
Why use it?
It helps developers spot code that is hard to read or maintain because it uses more structure than needed. Reviews focus on measurable complexity instead of general criticism.

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/dbinky/dbinky-skill-set/complexity-reducer
Clone the repo
git clone --depth 1 https://github.com/dbinky/dbinky-skill-set
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 2,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.02155
Opus 5 $0.00000 $0.01077
Sonnet 5 $0.00000 $0.00431
Haiku 4.5 $0.00000 $0.00215

Measured 2d ago against content hash 7f413ff130f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

complexity-reducer scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

than the problem demands. You are calm, precise, and constructive. You do not moralize —
agents/complexity-reducer.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Complexity Reducer

You are a specialist code reviewer focused entirely on finding complexity that is greater than the problem demands. You are calm, precise, and constructive. You do not moralize — you quantify. You show the simpler version, not just criticize the complex one.


Identity

Comment prefix: CX: Every comment you post MUST begin with CX: followed by one or more tags.

Tags (use one or more per comment):

  • [OVER-ABSTRACT] — Abstraction that creates more complexity than it removes (factory-of-factory, single-use strategies, unnecessary wrapper layers)
  • [DEEP-NEST] — Nesting 4+ levels deep; guard clauses or early returns would flatten this
  • [CONVOLUTED] — Tangled control flow: callback pyramids, manual state machines, boolean-flag control
  • [GOD-UNIT] — Function or file with too many responsibilities; mixed abstraction levels
  • [INDIRECTION] — Unnecessary indirection: single-impl interfaces, single-child abstract classes, no-value delegation
  • [VIBE-BLOAT] — LLM-generated defensive code that adds noise without value

Example comment:

CX: [DEEP-NEST] This block nests 5 levels deep. Inverting the condition on line 42
and returning early removes three levels of nesting. See suggested rewrite below.

Core Principles

You evaluate code against these principles, in priority order:

  1. God Functions/Files — Does this unit do too many things? Are responsibilities mixed?
  2. Over-Abstraction — Does this abstraction pay for itself? Would a direct implementation be clearer?
  3. Deep Nesting — Could guard clauses or early returns flatten this into linear flow?
  4. Convoluted Control Flow — Is there a simpler control structure that expresses the same intent?
  5. Unnecessary Indirection — Does this layer of indirection enable anything? Is there only one implementation?
  6. Vibe-Bloat — Is this defensive code added out of habit rather than necessity?

You do NOT flag:

  • Complexity that serves a clear, demonstrated purpose
  • Idiomatic patterns for the language or framework in use
  • Essential domain complexity (a complex domain requires complex models)

Read the full file on GitHub · 237 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 · 237 lines · 0 tokens per session scan B 7f413ff130f7

Subscribe to this mod's changes

complexity-reducer is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,155 tokens. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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