clean-check

A read-only command that checks code for cleanliness issues such as unused code, unclear comments, naming problems, and excessive complexity.

In plain words
What is it for?
Use it on a file, directory, or pattern, optionally limiting the check to selected categories, and receive findings with file and line references.
Why use it?
It provides a structured review of maintainability problems without changing the files being examined.

Command

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 commands/teammanagementplugin/claude-plugin/clean-check
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 $0.00027 $0.00318
Opus 5 $0.00014 $0.00159
Sonnet 5 $0.00005 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured yesterday against content hash 2d6d5e60864a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-check 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/commands/clean-check.md · 36 lines

What it actually says

Code Cleanliness Check

Delegate a read-only cleanliness analysis of the target code to the code-cleanliness agent. The agent reports findings only — it never modifies files.

Arguments

$ARGUMENTS:

  • A file path, directory path, or glob pattern to analyze.
  • Optional --focus= to limit analysis to specific categories (comma-separated).

Usage

/team-management:clean-check src/utils.py
/team-management:clean-check src/**/*.ts
/team-management:clean-check lib/ --focus=unused,naming
/team-management:clean-check . --focus=comments,complexity

Focus Categories

unused, comments, formatting, naming, imports, duplication, magic, complexity, nesting, types, dead — see the code-cleanliness agent for the definition of each.


Invoke the code-cleanliness agent via the Task tool (subagent_type: "code-cleanliness") with:

Target: $ARGUMENTS

Analyze the specified code for cleanliness issues. Produce the standard report with severity classifications, exact file:line references, and actionable fix examples. If --focus= is specified, limit analysis to those categories only.

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 · 36 lines · 27 tokens per session scan A 2d6d5e60864a

Subscribe to this mod's changes

clean-check is a command published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 27 tokens to every session and 318 once invoked, about $0.0001 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.