compare

compare is a command for coding agents from rohitg00/awesome-claude-code-toolkit. It costs 16 tokens per session (164 once invoked), scanned A, original, Apache-2.0.

An ML experiment comparison command that places several machine-learning runs side by side using their recorded settings and measurements.

In plain words
What is it for?
Use it to compare runs, study how settings affect results, create visualizations, and choose the next experiments to try.
Why use it?
It helps identify which configuration performs best without mixing runs that used different data or metrics.

Command

Part of the experiment-tracker plugin — 2 commands shipped together

About the project

Awesome Claude Code Toolkit is a curated collection of extensions and configuration for Claude Code, including agents, skills, commands, plugins, hooks, rules, templates, MCP configurations, and companion apps. It is for Claude Code users who want ready-made workflows and integrations for different development tasks. The catalogue add-ons are selected components from this toolkit.

rohitg00/awesome-claude-code-toolkit · 2,587 stars · on GitHub

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/rohitg00/awesome-claude-code-toolkit/compare
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Or install experiment-tracker, the plugin that ships this one along with the rest of its 2 commands.

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/rohitg00/awesome-claude-code-toolkit/compare.svg)](https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/compare)
Your own site
<a href="https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/compare"><img src="https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/compare.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 164 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 $0.00016 $0.00164
Opus 5 $0.00008 $0.00082
Sonnet 5 $0.00003 $0.00033
Haiku 4.5 $0.00002 $0.00016

Measured yesterday against content hash efe525af246a, 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 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.

plugins/experiment-tracker/commands/compare.md · 36 lines

What it actually says

Compare multiple ML experiment runs side-by-side to identify the best configuration.

Steps

  1. Load experiment records from the tracking store.
  2. Select experiments to compare:
  3. Build a comparison table:
  4. Analyze parameter sensitivity:
  5. Generate visualizations:
  6. Identify the winning configuration:
  7. Recommend next experiments to try.

Format

Comparison: <N> experiments
Best Run: <experiment name>
Key Findings:
  - <parameter X> has <impact> on <metric Y>

Rules

  • Only compare experiments with the same dataset version.
  • Use consistent metrics across all compared runs.
  • Statistical significance matters; do not draw conclusions from single runs.
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 · 36 lines · 16 tokens per session scan A efe525af246a

Subscribe to this mod's changes

compare is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,587 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 164 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 2026-09-03.