synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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/synthetic-sciences/openscience/generate-imagenpx skills add synthetic-sciences/openscience --skill generate-imagegit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/generate-image)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/generate-image"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/generate-image.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 | $0.00067 | $0.00808 |
| Opus 5 | $0.00034 | $0.00404 |
| Sonnet 5 | $0.00013 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
generate-image 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Image
Generate or edit a high-quality image with OpenScience's native generate_image tool. The tool keeps credentials in the trusted host and saves the returned image directly into the connected workspace.
Required route
Inside OpenScience, always call the native generate_image tool. Do not invoke scripts/generate_image.py through Bash: the native tool uses a connected Gemini or OpenRouter account and saves the result into the workspace.
Credential routing is automatic:
- A connected Gemini account is used when available.
- Otherwise, a connected user-owned OpenRouter key is used.
- Stop when neither account is connected or the selected provider rejects the request.
Never ask the user to paste a secret into chat. Direct them to Customize → Models to connect an account.
Tool contract
Call generate_image with:
prompt(required): detailed generation or editing instructions.output_path: destination in the connected workspace; defaultgenerated-image.png.input_path: existing image for an edit. Omit it entirely for a new image; never create or pass a blank canvas, directory,.or/dev/null.model: OpenRouter image model; defaultgoogle/gemini-3-pro-image(Nano Banana Pro).aspect_ratio: optional1:1,3:2,2:3,4:3,3:4,16:9, or9:16.
Example generation:
{
"prompt": "Editorial scientific illustration of a DNA double helix with one mutation site highlighted, restrained blue and amber palette, no decorative text",
"output_path": "figures/dna-mutation.png",
"aspect_ratio": "3:2"
}
Example edit:
{
"prompt": "Preserve every plotted value and label; improve spacing and contrast for a two-column conference paper",
"input_path": "figures/ablation-draft.png",
"output_path": "figures/ablation-refined.png",
"aspect_ratio": "4:3"
}
Model selection
google/gemini-3-pro-image: Nano Banana Pro; recommended for generation and editing.black-forest-labs/flux.2-pro: fast, high-quality generation and editing.black-forest-labs/flux.2-flex: cheaper generation-only alternative.
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.
- yesterday First seen · 78 lines · 67 tokens per session scan A 55ec6967055e
generate-image is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 808 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
llm-finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization.
ml-engineer
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
agentic-supply-chain-detection
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.
authorization-bypass-detection
Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.