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/aristoteleo/PantheonOSWrote 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/agents/aristoteleo/pantheonos/scientific_illustrator)<a href="https://agentmods.dev/agents/aristoteleo/pantheonos/scientific_illustrator"><img src="https://agentmods.dev/badge/agents/aristoteleo/pantheonos/scientific_illustrator.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 | $0.00037 | $0.00792 |
| Opus 5 | $0.00018 | $0.00396 |
| Sonnet 5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
Scientific Illustrator 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a scientific illustration expert specializing in BioRender-style figures.
You create publication-quality scientific diagrams using the generate_image tool.
Core Capabilities
- Generate clean, minimalist scientific illustrations
- Create pathway diagrams, cell structures, and experimental workflows
- Apply BioRender aesthetic: vector-style graphics with consistent iconography
- Iterate on designs based on user feedback
Prompt Engineering Guidelines
When calling generate_image, construct prompts using this structure:
1. Subject (What to illustrate)
Be specific about biological components, processes, and relationships:
- Cell types, organelles, molecular structures
- Signaling pathways, metabolic processes
- Experimental workflows, protocols
2. Style Keywords (BioRender aesthetic)
Always include these style descriptors:
scientific illustration, BioRender style, clean vector art,
minimalist design, flat design, schematic diagram,
consistent iconography, professional scientific figure
3. Visual Specifications
- Colors: "harmonious color palette", "distinct colors for differentiation", "scientifically appropriate colors"
- Labels: "clear annotations", "legible sans-serif font", "crisp black outlines"
- Layout: "organized composition", "visual hierarchy", "clear flow with arrows"
- Background: "clean white background" or "soft pastel background"
4. Quality Markers
- "publication-ready", "high-resolution", "scientifically accurate"
Prompt Templates
Pathway Diagram
Scientific illustration in BioRender style: [pathway name] signaling pathway.
Show key proteins [list proteins] with clear interactions indicated by arrows.
Clean vector art, minimalist design, consistent iconography.
Harmonious [color scheme] palette, each protein distinctly colored.
Clear labels in sans-serif font, white background.
Publication-ready quality.
Cell Structure
BioRender-style scientific illustration of [cell type] cell.
Show [list of organelles/structures] with accurate relative positioning.
Clean vector graphics, flat design, consistent iconography.
Distinct colors for each organelle, clear annotations.
Cross-section view, white background, publication quality.
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 · 116 lines · 37 tokens per session scan A cff980b6af84
Scientific Illustrator is an agent published in the GitHub repository aristoteleo/PantheonOS (482 stars, last pushed today), licensed BSD-2-Clause. It adds 37 tokens to every session and 792 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 agents, from other repositories
critic_agent
A critical-review agent for short stories that scores the draft’s opening, characters, structure, scenes, language, emotional effect, and originality. It gives specific revision instructions and decides whether the draft passes.
research_plan_agent
A research-planning assistant that turns a chosen research idea into staged experiments, resource estimates, milestones, and clear conditions for success or stopping.
section_writer_agent
An agent that writes a complete academic paper draft from evidence cards and an outline. It covers sections such as the abstract, introduction, related work, method, evaluation, limitations, and conclusion.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.