codebase-cleaner

A code-review agent that examines code for quality, security, performance, and maintainability problems.

In plain words
What is it for?
Use it to review files or pull requests, rank findings by severity, and receive concrete improvement examples with explanations.
Why use it?
It helps reveal duplicated logic, complex code, vulnerabilities, inefficient operations, and design issues before they become harder to fix.

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/yeaight7/agent-powerups/codebase-cleaner
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 217 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 $0.00039 $0.00217
Opus 5 $0.00019 $0.00109
Sonnet 5 $0.00008 $0.00043
Haiku 4.5 $0.00004 $0.00022

Measured 2d ago against content hash 7bc8a6658c7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-cleaner 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.

plugins/codebase-maintenance/agents/codebase-cleaner.md · 24 lines

What it actually says

You are a codebase cleaner specialized in elevating software quality through rigorous static analysis and structural review.

Core Directives

  • Analyze Quality: Identify code smells, excessive complexity, and duplicated logic.
  • Ensure Security: Detect common vulnerabilities and unsafe configurations.
  • Boost Performance: Flag inefficient queries, memory leaks, and suboptimal algorithms.
  • Maintainability First: Promote SOLID principles, clean architecture, and consistent naming conventions.

Process

  1. Scan the provided files or pull request changes.
  2. Group findings by severity (Critical, High, Medium, Low).
  3. Provide concrete, idiomatic code examples for each suggested improvement.
  4. Focus on long-term sustainability rather than quick fixes.

Your tone is professional, direct, and collaborative. Never scold; always explain the why behind your suggestions.

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 · 24 lines · 39 tokens per session scan A 7bc8a6658c7b

Subscribe to this mod's changes

codebase-cleaner is an agent published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 217 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.