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 skills add hairyf/skills --skill imaginegit clone --depth 1 https://github.com/hairyf/skillsWrote 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/hairyf/skills/imagine)<a href="https://agentmods.dev/skills/hairyf/skills/imagine"><img src="https://agentmods.dev/badge/skills/hairyf/skills/imagine/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/skills/hairyf/skills/imagine"><img src="https://agentmods.dev/badge/skills/hairyf/skills/imagine.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 | $0.00094 | $0.00879 |
| Opus 5 | $0.00047 | $0.00439 |
| Sonnet 5 | $0.00019 | $0.00176 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
imagine 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Gen
Generate images through scripts/imagine.js, a zero-dependency Node.js CLI (Node 18+, no npm install) backed by multiple providers. It saves images to disk and prints the absolute paths.
Quick start
# Generate an image
node scripts/imagine.js "a retro synthwave poster, neon grid, 80s style" -o poster.png
# Edit an existing image
node scripts/imagine.js "add a red balloon in the sky" -e photo.png -o edited.png
# Multi-step session: keep context across calls (design first, then its three views)
node scripts/imagine.js "a cute robot mascot, front view, flat vector style" --session mascot -o design.png
node scripts/imagine.js "draw its three views (front, side, back) from the same design" --session mascot -o views.png
# Clean up the session cache when the workflow is done
node scripts/imagine.js --clear mascot
Model selection
Priority for general images: GPT Image 2 (gpt-image-2) → Nano Banana (gemini-2.5-flash-image) → SiliconFlow Qwen-Image (Qwen/Qwen-Image) → OpenAI GPT Image (gpt-image-1). When a provider has no API key, fall back to the next configured one.
| Asset | Recommended models (priority order) |
|---|---|
| Images / posters | gpt-image-2 → gemini-2.5-flash-image → Qwen/Qwen-Image → gpt-image-1 |
| Stickers / icons / logos | Ideogram 3.0 (transparent) → gpt-image-1.5 / gpt-image-2 with --background transparent -f png → FLUX.2 pro |
| Seamless textures | Z-Image Turbo Tiling (fal.ai) → FLUX.2 pro → any strong model with a strict tiling prompt |
Specialist models outside the script's providers (Ideogram, fal tiling) are called through their own APIs; imagine.js covers OpenAI, SiliconFlow, Gemini, and OpenAI-compatible relays.
Key workflows
- Transparent assets:
--background transparent -f png(neverjpeg); phrase stickers as "die-cut sticker, thick white border, bold clean shapes". - Seamless textures: include "seamless, tileable, top-down, flat uniform lighting, no shadows, edges wrap perfectly".
- Text in images: GPT Image 2 is best for CJK/multilingual text; keep text short and quoted.
- Aspect ratio: Gemini via
--aspect 16:9; OpenAI/SiliconFlow via-s WxH(Qwen native sizes like1328x1328,1664x928). - Iterate cheaply: draft with
Qwen/Qwen-Image/ Nano Banana or-q low, render finals ongpt-image-2with-q high;--seedfor reproducible output.
What ships with it
11 files 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.
- AGENTS.md 1.5 KB
- references/core-script.md 5.8 KB
- references/core-setup.md 1.9 KB
- references/core-usage.md 4.0 KB
- scripts/imagine.js 9.2 KB runs code
- scripts/lib/config.js 1.4 KB runs code
- scripts/lib/env.js 1.3 KB runs code
- scripts/lib/http.js 4.7 KB runs code
- scripts/lib/output.js 2.3 KB runs code
- scripts/lib/providers.js 6.8 KB runs code
- scripts/lib/session.js 1.9 KB runs code
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 · 57 lines · 94 tokens per session scan A 711e0ccc140e
imagine is a skill published in the GitHub repository hairyf/skills (25 stars, last pushed 29d ago), licensed MIT. It adds 94 tokens to every session and 879 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.