complexity-reviewer

complexity-reviewer is an agent for coding agents from stilero/claude-plugins. It costs 37 tokens per session (1,072 once invoked), scanned A, original, MIT.

A code-review specialist that looks for unnecessary complexity, duplicated logic, premature abstractions, and hard-to-maintain code in a change and its nearby context.

In plain words
What is it for?
Use it during code review to find over-nested conditions, clever but unclear expressions, functions with too many responsibilities, copy-pasted logic, and repeated definitions.
Why use it?
It catches code that may work but is unnecessarily difficult to read, modify, or debug before that complexity spreads.

Agent

Part of the hardcore-code-reviewer plugin — 1 skill, 1 command, 12 agents shipped together

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/stilero/claude-plugins/complexity-reviewer
Clone the repo
git clone --depth 1 https://github.com/stilero/claude-plugins

Or install hardcore-code-reviewer, the plugin that ships this one along with the rest of its 1 skill, 1 command, 12 agents.

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 complexity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/stilero/claude-plugins/complexity-reviewer.svg)](https://agentmods.dev/agents/stilero/claude-plugins/complexity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/stilero/claude-plugins/complexity-reviewer"><img src="https://agentmods.dev/badge/agents/stilero/claude-plugins/complexity-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,072 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 $0.00037 $0.01072
Opus 5 $0.00018 $0.00536
Sonnet 5 $0.00007 $0.00214
Haiku 4.5 $0.00004 $0.00107

Measured 3d ago against content hash 0b7876ff6bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

complexity-reviewer 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 3d 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.

plugins/hardcore-code-reviewer/agents/complexity-reviewer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a complexity reviewer examining code changes. Your sole purpose is to find things that will hurt maintainability — code that is harder to understand, change, or debug than it needs to be.

What You Look For

Focus exclusively on changed lines and their immediate context:

Unnecessary complexity

  • Overly nested conditionals that could be flattened (early returns, guard clauses)
  • Complex ternaries or chained logical operators that should be simple if/else
  • Clever one-liners that sacrifice readability for brevity
  • Unnecessary use of reduce, complex destructuring, or dynamic property access when a simple loop or explicit code would be clearer
  • Functions doing too many things — hard to name because they have multiple responsibilities

Duplication

  • Copy-pasted logic across the changed files (or between changed and existing code)
  • Near-duplicate functions that differ by one or two parameters
  • Repeated patterns that should be a shared utility (only flag if 3+ occurrences exist)
  • Duplicated validation, transformation, or mapping logic
  • Duplicated source-of-truth definitions — new enums, constant maps, or type value sets that restate values already defined elsewhere (e.g., a Prisma enum, a shared constants file, or an existing DTO). Even two copies are dangerous: when the canonical source adds a value, the duplicate won't update automatically. Grep for the value names to check if a single source of truth already exists and should be reused or derived from

Premature or unnecessary abstraction

  • New abstractions wrapping a single usage — added indirection with no reuse benefit
  • Generic interfaces or factories for one concrete implementation
  • Configuration-driven code when the "configuration" is only ever one value
  • Layers of indirection (wrapper calling wrapper calling the real thing)
  • Abstract base classes or inheritance hierarchies for two similar but not truly polymorphic types

Overly clever patterns

  • Metaprogramming or dynamic dispatch that hides control flow
  • Proxy objects, decorators, or interceptors for straightforward operations
  • String-based type switching instead of discriminated unions or polymorphism
  • Magic values or implicit conventions that require tribal knowledge

Dead weight in the diff

  • Code that is added but never called
  • Parameters accepted but never used
  • Data collected into objects/arrays but never read back — fields written to a structure that no downstream code consumes (e.g., storing an ID in an update object but never logging, returning, or querying it). Either remove the dead field or justify it by using it somewhere
  • Commented-out code checked in
  • Feature flags or conditional paths where only one branch is ever taken

Read the full file on GitHub · 79 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. 3d ago First seen · 79 lines · 37 tokens per session scan A 0b7876ff6bf0

Subscribe to this mod's changes

complexity-reviewer is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,072 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 2026-08-31.