review-duplicates

review-duplicates is a command for Claude Code from nwiizo/ccswarm. It costs 0 tokens per session (956 once invoked), scanned A, original, MIT.

A command for finding semantically similar or duplicated code in a Rust codebase. It uses similarity-rs and can show matching code and configurable similarity thresholds.

In plain words
What is it for?
Use it to scan the crates directory, adjust the similarity or minimum-size settings, print matching code, and identify possible refactoring candidates.
Why use it?
It helps reveal places where the same logic appears more than once, so developers can decide whether to combine it and reduce maintenance work.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it to scan the crates directory, adjust the similarity or minimum-size settings, print matching code, and identify possible refactoring candidates.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/nwiizo/ccswarm/review-duplicates
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.

Clone the repo
git clone --depth 1 https://github.com/nwiizo/ccswarm

Made for: Claude Code.

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 review-duplicates

README.md
[![agentmods](https://agentmods.dev/badge/commands/nwiizo/ccswarm/review-duplicates.svg)](https://agentmods.dev/commands/nwiizo/ccswarm/review-duplicates)
Your own site
<a href="https://agentmods.dev/commands/nwiizo/ccswarm/review-duplicates"><img src="https://agentmods.dev/badge/commands/nwiizo/ccswarm/review-duplicates.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 956 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00956
Opus 5 $0.00000 $0.00478
Sonnet 5 $0.00000 $0.00191
Haiku 4.5 $0.00000 $0.00096

Measured 8d ago against content hash a8f59bf3ebd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-duplicates 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 8d 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.

.claude/commands/review-duplicates.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Duplicate Code Detection

Uses similarity-rs to detect semantically similar code in the codebase and identify refactoring candidates.

Execution Method

# Basic execution (analyze crates/ directory)
similarity-rs crates/

# Specify similarity threshold (default: 0.85)
similarity-rs crates/ --threshold 0.80

# Include code in output
similarity-rs crates/ --print

# Specify minimum lines (default: 3 lines)
similarity-rs crates/ --min-lines 5

Options

Option Description Default
--threshold Similarity threshold (0.0-1.0) 0.85
--print Include code in output false
--min-lines Minimum lines 3
--min-tokens Minimum tokens 30
--extensions Target file extensions rs

Detection Patterns

Refactoring Priority

Priority Condition Action
High 95%+ similarity, 10+ lines Extract to common function
Medium 90-95% similarity, 5+ lines Consider trait or macro conversion
Low 85-90% similarity Check structural similarity, extract if needed

Acceptable Duplication

The following may be detected as duplicates but often don't need refactoring:

  1. Test code - Prioritize test independence
  2. Configuration structs - Similar configuration patterns
  3. Error handling - Context-dependent error processing
  4. ClaudeCodeConfig initialization - Explicit field specification is preferred

Output Format

{
  "duplicate_analysis": {
    "total_functions": N,
    "similar_pairs": N,
    "high_priority": [
      {
        "file1": "path1",
        "file2": "path2",
        "lines1": "L10-L30",
        "lines2": "L50-L70",
        "similarity": "97%",
        "action": "Extract to common function"
      }
    ],
    "medium_priority": [],
    "low_priority": [],
    "ignored": [
      {
        "reason": "Test code",
        "count": N
      }
    ]
  }
}

ccswarm-Specific Refactoring Strategies

Read the full file on GitHub · 146 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. 8d ago First seen · 146 lines · 0 tokens per session scan A a8f59bf3ebd3

Subscribe to this mod's changes

review-duplicates is a command published in the GitHub repository nwiizo/ccswarm (151 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 956 tokens. 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 2026-08-30.