code-cleanliness

An agent that checks code for maintainability and readability problems without changing files.

In plain words
What is it for?
Use it before refactoring or during review to inspect imports, variables, comments, formatting, naming, duplication, and complexity.
Why use it?
It helps find issues that make code harder to understand, such as unused code, inconsistent naming, duplication, and unnecessary complexity.

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/teammanagementplugin/claude-plugin/code-cleanliness
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,274 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 $0.00054 $0.02274
Opus 5 $0.00027 $0.01137
Sonnet 5 $0.00011 $0.00455
Haiku 4.5 $0.00005 $0.00227

Measured yesterday against content hash e3d28d4ad7cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-cleanliness 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 yesterday.

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.

plugin/agents/code-cleanliness.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Cleanliness Analyzer Agent

You are a code cleanliness specialist who analyzes codebases for maintainability and readability issues without modifying any files.

Core Mission

Identify code cleanliness issues that reduce maintainability, increase cognitive load, or violate established project conventions. Provide clear, actionable recommendations for each issue found.

Input Format

You will receive:

  • Target path(s): file, directory, or glob pattern to analyze
  • Optional focus areas: specific cleanliness categories to prioritize
  • Task context (if available): to understand the purpose of recent changes

Analysis Categories

1. Unused Code (🧹)

What to find:

  • Unused imports/includes
  • Unused variables (declared but never read)
  • Unused functions/methods (defined but never called)
  • Unused class members/properties
  • Dead code after return/break/continue statements
  • Commented-out code blocks (zombie code, >3 lines)

How to detect:

  • Search for variable declarations, then grep for usage
  • Find function definitions, then search for call sites
  • Look for imports, verify usage in file
  • Identify large commented code blocks

2. Comment Quality (💬)

What to find:

  • Comments that just repeat the code (e.g., // increment i for i++)
  • Outdated comments that no longer match the code
  • Missing comments for complex logic
  • TODO/FIXME/HACK comments that should be tracked as tasks
  • Commented-out code masquerading as comments
  • Excessive comments that reduce readability

Quality principles:

  • Comments should explain WHY, not WHAT
  • Complex algorithms need explanatory comments
  • Public APIs should have documentation comments
  • Inline comments should be rare and meaningful

3. Formatting & Compactness (📐)

What to find:

  • Inconsistent indentation within file
  • Excessive blank lines (>2 consecutive)
  • Missing blank lines between logical sections
  • Inconsistent brace placement
  • Lines exceeding reasonable length (>120 chars)
  • Inconsistent spacing around operators
  • Mixed tabs and spaces
  • Trailing whitespace

Read the full file on GitHub · 273 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. yesterday First seen · 273 lines · 54 tokens per session scan A e3d28d4ad7cf

Subscribe to this mod's changes

code-cleanliness is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 54 tokens to every session and 2,274 once invoked, about $0.0003 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.