compare

compare is a command for coding agents from qazi0/claude-plugins. It costs 20 tokens per session (518 once invoked), scanned A, original, MIT.

A command that compares two public GitHub repositories side by side. A repository is a project's source code, documentation, and related files hosted on GitHub.

In plain words
What is it for?
Use it to compare purpose, architecture, features, performance information, integrations, documentation, learning difficulty, and design trade-offs.
Why use it?
It gathers comparable information about both projects so you can examine differences without researching each one separately.

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/qazi0/claude-plugins/compare
Clone the repo
git clone --depth 1 https://github.com/qazi0/claude-plugins

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 compare

README.md
[![agentmods](https://agentmods.dev/badge/commands/qazi0/claude-plugins/compare.svg)](https://agentmods.dev/commands/qazi0/claude-plugins/compare)
Your own site
<a href="https://agentmods.dev/commands/qazi0/claude-plugins/compare"><img src="https://agentmods.dev/badge/commands/qazi0/claude-plugins/compare.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 518 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 $0.00020 $0.00518
Opus 5 $0.00010 $0.00259
Sonnet 5 $0.00004 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 3d ago against content hash 83fc1e892e9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare 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 3d 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.

deepwiki/commands/compare.md · 67 lines

What it actually says

Compare Repositories

You are comparing two GitHub repositories:

  • Repository 1: $ARGUMENTS.repo1
  • Repository 2: $ARGUMENTS.repo2
  • Focus Aspect: $ARGUMENTS.aspect

Instructions

  1. First, gather information about both repositories in parallel:

    • Use read_wiki_structure for both repos to understand their documentation structure
    • Use ask_question for both repos with targeted questions about their core purpose and architecture
  2. For each repository, gather:

    • Core purpose and philosophy
    • Key features and capabilities
    • Architecture and design patterns
    • Performance characteristics (if available)
    • Ecosystem and community (plugins, extensions, integrations)
    • Learning curve and documentation quality
  3. If a specific aspect was provided ("$ARGUMENTS.aspect"), dive deeper:

    • Use ask_question on both repos specifically about that aspect
    • Compare their approaches, trade-offs, and implementations
  4. Present a structured comparison:

    Overview

    Brief description of what each project is and its primary use case.

    Philosophy & Approach

    How each project approaches the problem domain.

    Feature Comparison

    Feature $ARGUMENTS.repo1 $ARGUMENTS.repo2
    ... ... ...

    Architecture

    Key architectural differences and similarities.

    When to Choose Each

    • Choose $ARGUMENTS.repo1 when: [specific use cases]
    • Choose $ARGUMENTS.repo2 when: [specific use cases]

    Trade-offs

    What you gain and lose with each choice.

  5. Be objective and factual. Avoid bias toward either repository.

  6. If information is limited for either repository, acknowledge this and suggest what additional research might be needed.

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. 3d ago First seen · 67 lines · 20 tokens per session scan A 83fc1e892e9d

Subscribe to this mod's changes

compare is a command published in the GitHub repository qazi0/claude-plugins (8 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 518 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.