refactor-cleaner

refactor-cleaner is an agent for Claude Code from vasuag09/harness-claude. It costs 44 tokens per session (291 once invoked), scanned A, original, MIT.

A code-cleanup assistant that finds unused code, repeated logic, dead branches, debugging leftovers, and overly large files while preserving behavior.

In plain words
What is it for?
Checking whether code is still used, removing safe leftovers, consolidating duplication, and verifying the project with tests or builds.
Why use it?
It reduces maintenance work and technical debt without changing what the software does.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the harness-claude plugin — 34 skills, 8 agents, 6 hooks, 3 MCP servers 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/vasuag09/harness-claude/refactor-cleaner
Clone the repo
git clone --depth 1 https://github.com/vasuag09/harness-claude

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 34 skills, 8 agents, 6 hooks, 3 MCP servers.

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 refactor-cleaner

README.md
[![agentmods](https://agentmods.dev/badge/agents/vasuag09/harness-claude/refactor-cleaner.svg)](https://agentmods.dev/agents/vasuag09/harness-claude/refactor-cleaner)
Your own site
<a href="https://agentmods.dev/agents/vasuag09/harness-claude/refactor-cleaner"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/refactor-cleaner.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 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 5.1 $0.00044 $0.00291
Opus 5 $0.00022 $0.00146
Sonnet 5 $0.00009 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured 5d ago against content hash 1647a8037da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

refactor-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 5d 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.

agents/refactor-cleaner.md · 28 lines

What it actually says

You reduce the codebase safely without changing behavior.

Method

  1. Identify candidates: unused exports/imports/files, dead branches, duplicated logic, stray debug code, oversized files (>800 lines). Use available analyzers (knip/depcheck/ts-prune/ruff/vulture) when present; else mgrep/Grep.
  2. Verify a thing is truly unused before deleting — check all references and dynamic usage. When unsure, leave it and report instead.
  3. Make small, reversible changes. Run tests/build after each meaningful step.
  4. Consolidate duplication into a single well-named utility (DRY), splitting oversized files by responsibility.

Constraints

  • Behavior-preserving only. No feature changes, no API changes without being asked.
  • Never delete something you didn't confirm is unused.
  • Keep diffs reviewable; stop and report if a "cleanup" turns into a redesign.

Output

What was removed/consolidated (with reference checks), what was left and why, and confirmation tests/build still pass.

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. 5d ago First seen · 28 lines · 44 tokens per session scan A 1647a8037da7

Subscribe to this mod's changes

refactor-cleaner is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 291 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.

Related

Other agents, from other repositories

adr-writer

Architecture Decision Record generator agent — read-only. Detects architectural decisions in code changes, classifies criticality, and generates ADRs in the pattern-oriented ADR format by Michael Nygard (context-decision-consequences). Never modifies code. Use after significant changes or when a decision needs…

FlorianBruniaux/claude-code-plugins · 64 tokens

code-reviewer

Use for thorough code review with quality, security, and performance checks.

FlorianBruniaux/claude-code-plugins · 17 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-plugins · 57 tokens

report-template

Monthly evaluation template for scoring analytics agent performance and accuracy.

FlorianBruniaux/claude-code-plugins · 10 tokens

loop-monitor

Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.

FlorianBruniaux/claude-code-plugins · 34 tokens

architecture-reviewer

Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.

FlorianBruniaux/claude-code-plugins · 45 tokens