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 skills/suxrobgm/rasterize/rendernpx skills add suxrobGM/rasterize --skill rendergit clone --depth 1 https://github.com/suxrobGM/rasterizeWhat 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 | $0.00038 | $0.01742 |
| Opus 5 | $0.00019 | $0.00871 |
| Sonnet 5 | $0.00008 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
render 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 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.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rasterize — Multi-Engine Raster Image Generation
Generate professional raster images by routing each request to the best rendering engine. You write Python code; the engine does the pixel work.
Quick Start
- Read the user's request
- Pick an engine using the routing table below
- Read the engine's reference doc from
./references/ - Write a self-contained Python script that outputs to the target path
- Run the script using
pdm run python <script.py>(to use the plugin's venv), verify the output, deliver the image
Environment: This plugin uses a pdm-managed virtual environment. Always run generation scripts with
pdm run pythonfrom the plugin root. If pdm is not set up yet, runpython scripts/setup.pyfirst.
Engine Routing Table
| Request type | Engine | Reference file |
|---|---|---|
| Photo manipulation, compositing, filters, pixel ops, simple graphics | Pillow | ./references/pillow.md |
| Clean vector-style graphics, logos, icons, anti-aliased shapes, typography-heavy designs | Cairo | ./references/cairo.md |
| Statistical charts, scientific plots, data visualization (static) | Matplotlib + Seaborn | ./references/matplotlib.md |
| Complex interactive-looking dashboards, rich data viz with annotations | Plotly (static export) | ./references/plotly.md |
| Complex layouts, HTML/CSS designs, UI mockups, anything with web fonts or CSS effects | Playwright (HTML→PNG) | ./references/playwright.md |
Routing decision hints
- If the request mentions "chart", "plot", "graph", "histogram", "scatter", "heatmap", or data columns → Matplotlib/Seaborn (or Plotly for fancier output)
- If the request is about a logo, icon, badge, geometric design, or anything that needs crisp anti-aliased curves → Cairo
- If the request says "banner", "social media post", "thumbnail" with text overlays on photos → Pillow
- If the request describes a full-page layout, poster with complex typography, card design, or UI mockup → Playwright
- If the request is about generative/procedural/algorithmic art → Cairo (or Pillow if it's pixel-manipulation art like fractals)
- When in doubt between Pillow and Cairo → prefer Cairo (better quality)
- When in doubt between Matplotlib and Plotly → prefer Matplotlib (simpler, faster)
What ships with it
9 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.
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 · 171 lines · 38 tokens per session scan A aca285f4823e
render is a skill published in the GitHub repository suxrobGM/rasterize (4 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,742 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 2026-08-31.
Other skills, from other repositories
tweet-card-generator
Given a topic, auto-searches for info, generates a tweet + matching data-card PNG (HTML→screenshot, clean cream-background style, multi-layout + multi-chart).
image-generation
Generate and edit AI images using Gemini or OpenAI. Text-to-image, text-based editing, iterative refinement.
gemini-api
Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inputs, tools, media…
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
muapi-media-generation
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.