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.
git clone --depth 1 https://github.com/imaginpro/imaginepro-claude-pluginWrote 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.
[](https://agentmods.dev/commands/imaginpro/imaginepro-claude-plugin/vary-it)<a href="https://agentmods.dev/commands/imaginpro/imaginepro-claude-plugin/vary-it"><img src="https://agentmods.dev/badge/commands/imaginpro/imaginepro-claude-plugin/vary-it/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/imaginpro/imaginepro-claude-plugin/vary-it"><img src="https://agentmods.dev/badge/commands/imaginpro/imaginepro-claude-plugin/vary-it.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01517 |
| Opus 5 | $0.00000 | $0.00758 |
| Sonnet 5 | $0.00000 | $0.00303 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
vary-it 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create intelligent variations and refinements of an existing ImaginePro generated image.
This command smartly decides the best approach for creating variations based on your request, using the appropriate MCP tool (variant, reroll, or inpaint).
Usage
# Random variation
/vary-it [messageId]
# Guided variation with description
/vary-it [messageId] [what to change]
How It Works
/vary-it intelligently chooses the right technique:
Random Variation (No Description)
/vary-it abc123
Uses the create-variant tool to generate alternative versions exploring different interpretations while maintaining the core concept.
Reroll (Same Prompt, Different Result)
/vary-it abc123 try a completely different take
Uses the reroll-image tool to regenerate from the same original prompt with different random seed.
Guided Changes (Future: Inpainting)
/vary-it abc123 make the background mountains instead of ocean
Currently suggests using the inpaint-image tool with a mask for targeted regional changes.
Common Use Cases
Exploring Alternatives
# Generate initial image
/imagine-pro modern office workspace, minimalist, blue tones
# Explore variations
/vary-it [messageId] # Get 2-3 alternative interpretations
Refining Details
# Initial generation
/imagine-pro product hero image for wireless earbuds
# Adjust colors
/vary-it [messageId] make colors warmer and more inviting
# Try different angle
/vary-it [messageId] show from a different perspective
A/B Testing
# Original version
/imagine-pro landing page hero image, SaaS product
# Create test variants
/vary-it [messageId] # Variant A
/vary-it [messageId] # Variant B
/vary-it [messageId] # Variant C
# Test all, upscale winner
/upscale-it [winning-messageId]
Iteration Workflow
# Round 1
/imagine-pro professional team collaboration scene
# Result: msg-001
# Round 2 - Explore variations
/vary-it msg-001
# Result: msg-002 (like this direction!)
# Round 3 - Refine the variant
/vary-it msg-002 add more natural lighting
# Result: msg-003 (perfect!)
# Finalize
/upscale-it msg-003
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.
- 9d ago First seen · 256 lines · 0 tokens per session scan A e43b78579e14
vary-it is a command published in the GitHub repository imaginpro/imaginepro-claude-plugin (5 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,517 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 2026-08-31.
Other commands, from other repositories
make-reel
Generate a cinematic vertical reel via the Poppify MCP — photo-led or topic-led. Uses the poppify-build-reel skill for the canonical flow.
troubleshoot
Diagnose a Poppify reel that came out wrong. Walks the symptom → root cause → action decision tree.
verify-render
Download a rendered Poppify reel, run ffprobe + frame extract, surface a verdict on whether the render matches what was requested.
imagegen
Generate an image (or a coherent set of images) from a prompt — /imagegen " ". Or run /imagegen setup to verify the install. Routes through the imagegen MCP server (Codex CLI / gpt-image).
edit
Edit an existing image at a given path with a natural-language instruction. Routes through Codex CLI's gpt-image edit tool.
img
Alias of /imagegen. Generate an image from a prompt and save it under the workspace's standard image directory.