compare

A command that generates matching image prompts with Google and OpenAI image providers for side-by-side comparison.

In plain words
What is it for?
Use it to compare generated images, provider results, and expected costs for the same prompt.
Why use it?
It helps reveal which provider better suits a particular image request and records comparison details and estimated costs.

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/thrownlemon/claude-code-plugins/compare
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00009 $0.00702
Opus 5 $0.00005 $0.00351
Sonnet 5 $0.00002 $0.00140
Haiku 4.5 $0.00001 $0.00070

Measured yesterday against content hash 180b52f703a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

compare scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman
plugins/imagegen/commands/compare.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

  1. Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution"$(rm -rf /)" still executes inside double quotes.
  2. Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
  3. Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

Compare Providers

Generate the same prompt with both Google Gemini and OpenAI GPT-Image for side-by-side comparison. Useful for evaluating which provider produces better results for your specific use case.

What Gets Generated

  • One image from Google Gemini
  • One image from OpenAI GPT-Image
  • Metadata file with comparison details
  • Estimated costs for each provider

Examples

/imagegen:compare --prompt "A futuristic spaceship in orbit"
/imagegen:compare --prompt "Portrait of a wise old wizard" --google-model gemini-3-pro-image-preview
/imagegen:compare --prompt "Product photo of headphones" --size 16:9

Execution

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/compare.py \
  --prompt "$ARGUMENTS.prompt" \
  ${ARGUMENTS.google-model:+--google-model "$ARGUMENTS.google-model"} \
  ${ARGUMENTS.openai-model:+--openai-model "$ARGUMENTS.openai-model"} \
  ${ARGUMENTS.size:+--size "$ARGUMENTS.size"}

Output

Creates a comparisons/ folder with:

  • compare_TIMESTAMP_google.png - Google's result
  • compare_TIMESTAMP_openai.png - OpenAI's result
  • compare_TIMESTAMP_meta.json - Metadata and costs

Comparison Factors

Consider these when comparing:

  • Quality: Detail, sharpness, artifacts
  • Prompt adherence: How well it matches the description
  • Style: Artistic interpretation differences
  • Text rendering: If prompt includes text
  • Cost: Price per image
  • Speed: Generation time

Read the full file on GitHub · 80 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. yesterday First seen · 80 lines · 0 tokens per session scan C 180b52f703a0

Subscribe to this mod's changes

compare is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 702 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.