Borrowing it
Nothing to install: this file belongs to Sma1lboy/rove. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Sma1lboy/rove/main/.claude/skills/image-gen/SKILL.mdgit clone --depth 1 https://github.com/Sma1lboy/roveWrote 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/skills/sma1lboy/rove/image-gen)<a href="https://agentmods.dev/skills/sma1lboy/rove/image-gen"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/image-gen.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00923 |
| Opus 5 | $0.00021 | $0.00462 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
image-gen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-gen
Generate one image from a text prompt via MiniMax image-01 model. The output file is written to the filename you pass as the 4th argument (relative to the caller's cwd).
The script path is resolved relative to this SKILL.md (not the caller's cwd), so it works from any directory. It accepts exactly four positional arguments: prompt, width, height, output_filename.
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
python3 "$SCRIPT_DIR/scripts/image-gen.py" "<prompt>" <width> <height> <output_filename>
| Argument | Type | Constraints |
|---|---|---|
| prompt | string | ≤ 1500 chars; describe subject + style + mood |
| width | int | 512–2048, must be a multiple of 8 |
| height | int | 512–2048, must be a multiple of 8 |
| output_filename | string | Filename to write the image to, relative to cwd (e.g. img1.png). The file extension is preserved as-is. |
Output
- File:
<output_filename>(relative to cwd — the directory the command is invoked from) - Format: raw image bytes base64-decoded from the API response; extension is whatever you pass (e.g.
.png,.jpeg) - Always overwrites an existing file at the same path
After running, confirm the file exists with ls -lh <output_filename> and report the absolute path to the user.
Prompt writing tips
Be explicit about style to avoid photorealistic defaults. Example style keywords:
- Flat / UI / vector:
UI style,flat illustration,vector art,minimalist,clean cut-and-paste aesthetic,no photography no realistic textures - Collage / cut-and-paste:
paper cut collage,layered flat cut-out shapes,torn paper edges,mixed media - Vintage / retro:
vintage paper collage,sun-faded tones,retro travel poster - Photorealistic:
photorealistic,documentary photography,film grain
Combine subject + style + palette. Example structure:
"<style keywords>: <subject>, <key visual elements>, <color palette>, <negative constraints>"
Examples
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 72 lines · 42 tokens per session scan A 8b6db9cbbe9e
image-gen is a skill published in the GitHub repository Sma1lboy/rove (119 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 923 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pptx
Create, read and edit Microsoft PowerPoint .pptx presentations — slide decks with titles, bullets, images, tables, charts, speaker notes and consistent branding. Also covers building on a corporate template while keeping its theme, reading an existing deck's content, and rendering slides to images to check they…
make-a-deck
Use when building 16:9 presentation slide decks, visual storyboards, or pitch decks.
animated-video
Use when creating animated product launch videos, GSAP timelines, or visual motion assets.
flier
Use when designing marketing fliers, single-page promotional posters, or social media cards.
maps-geography
Use when embedding interactive maps, geospatial charts, or Leaflet/Mapbox visualizations.
3d-object
Use when modeling 3D objects, interactive scenes, or inspection models with Three.js.