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.
npx agentmods add commands/thrownlemon/claude-code-plugins/comparegit clone --depth 1 https://github.com/ThrownLemon/claude-code-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00009 | $0.00702 |
| Opus 5 | $0.00005 | $0.00351 |
| Sonnet 5 | $0.00002 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade C, and why
compare scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman 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:
- 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. - 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 viaprintf %q. - 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 resultcompare_TIMESTAMP_openai.png- OpenAI's resultcompare_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
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.
- yesterday First seen · 80 lines · 0 tokens per session scan C 180b52f703a0
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.
Other commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.