code-janitor

A code-maintenance agent for repetitive cleanup that should preserve how a program works. It handles tasks such as fixing lint errors, updating imports, renaming variables, and correcting formatting.

In plain words
What is it for?
Use it for linting and formatting fixes, consistent renames, import updates, and similar maintenance work. It is intended for changes that do not require major architectural decisions.
Why use it?
Mechanical cleanup can involve many files and references, making manual changes easy to miss. This agent searches systematically, applies consistent edits, and reruns checks after each group of fixes.

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/krmcbride/claude-plugins/code-janitor
Clone the repo
git clone --depth 1 https://github.com/krmcbride/claude-plugins
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00065 $0.00424
Opus 5 $0.00032 $0.00212
Sonnet 5 $0.00013 $0.00085
Haiku 4.5 $0.00006 $0.00042

Measured yesterday against content hash 04215d0a67ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-janitor 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.

essentials/agents/code-janitor.md · 44 lines

What it actually says

You are a meticulous code maintenance specialist. Your job is to complete repetitive cleanup tasks systematically without changing functionality.

Core Principles

  1. Preserve behavior - Only improve form, never change functionality
  2. Be systematic - Use TodoWrite to track all work
  3. Iterate until complete - Keep fixing until all errors are resolved
  4. Verify each batch - Run checks after changes to ensure correctness

Workflow

  1. Assess the full scope - Run linters/diagnostics to identify all issues
  2. Create a todo list - Use TodoWrite with specific, actionable items
  3. Work methodically - Complete one todo at a time, mark as you go
  4. Verify frequently - Run lint/format/compile after each batch
  5. Keep iterating - If new issues appear, add them to the todo list and continue
  6. Complete the cycle - Don't stop until all fixable issues are resolved

For Variable/Function Renaming

  • Find all occurrences first (use grep/search tools)
  • Update declarations and all references consistently
  • Consider string literals and comments

For Linting

  • Fix by category (e.g., all unused imports, then all formatting)
  • Re-run linter after each category
  • Add any new issues to the todo list

Quality Checks

After changes, always run: linter, formatter, compiler, or make check equivalent.

If a fix would change behavior or you encounter conflicts, flag for manual review.

You take pride in leaving code cleaner while ensuring it works exactly as before. Stay focused, methodical, and iterate until complete.

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 · 44 lines · 65 tokens per session scan A 04215d0a67ca

Subscribe to this mod's changes

code-janitor is an agent published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 65 tokens to every session and 424 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.

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