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 xuzhougeng/ScientificFigureLibrary --skill figure-librarygit clone --depth 1 https://github.com/xuzhougeng/ScientificFigureLibraryWrote 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/xuzhougeng/scientificfigurelibrary/figure-library)<a href="https://agentmods.dev/skills/xuzhougeng/scientificfigurelibrary/figure-library"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-library/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/xuzhougeng/scientificfigurelibrary/figure-library"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 618 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Rogue Agent · line 40 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.07639 |
| Opus 5 | $0.00021 | $0.03819 |
| Sonnet 5 | $0.00008 | $0.01528 |
| Haiku 4.5 | $0.00004 | $0.00764 |
Grade A, and why
figure-library 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 today.
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 — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Figure Library 0.6.8
Use this Skill when a user wants to store an uploaded figure/code pair, review or publish a local template, search for a plotting reference, or materialize an exact template into a project.
Version 0.6.1 adds the bundled Open Figure Modules Provider while keeping
materialization protocol v2, review truthfulness, and the transport image
adapter. Default search is Local Published, FigureYa, bundled Personal Figure
Modules, then opted-in dynamic personal sources. Community remains readable
for an explicit providerId, but is frozen and excluded from default search.
The MCP App may request fullscreen or
pip when the Host advertises those display modes. Wisp, Codex, and Claude
plugin packages all ship this Skill beside the same MCP server. Optional
scientificQuestion explains why a figure is worth drawing; it is not
description or visualProfile. There is no receipt-free materialization
path.
Bundled companion Skills
Use the copies shipped beside this Skill, not similarly named Host installations.
- Before creating/updating template prose use figure-description. Pass independent Markdown description/application/dataProfile, with a non-empty application for every new/updated Working revision. Never put scenarios into visualProfile.
- When the user actually requests adapting/replicating a selected template, use figure-organization, then figure-style. Preserve reference fidelity by default.
- Pure search/preview/materialization does not start prose writing or plotting.
- Host execution tools and the project R/Python environment are still needed. A plugin installation is not approval to execute code or install packages.
Non-negotiable boundaries
- The Library is one user-selected, cross-project global store. Never infer the Library root from the current project and never create a project pin.
- Standard core uses direct image/code intake. Do not call
figure_capture_*; Capture tools are not registered in the standard 0.6 server. - The server hashes, validates, versions, reviews, and materializes files. It does not contain a model and never executes code.
- Host Agent observations, deterministic/rule findings, and user decisions are distinct. Do not present an Agent inference as source fact or user approval.
- Plot
not_runnever means reproduced, validated, or verified. Plot execution, upstream workflow, and scientific validation are separate claims. - Treat all code and materialized files as untrusted. Never run a dependency installer automatically.
- Public Provider materialization only downloads, verifies, extracts, and
writes. Never execute R, Python, notebooks, shell, or installers from a
template.
codeExecutedBySflClientmust remainfalse. - Central curation, a publisher signature, and the recipient's Local review are separate facts. Never call a Community/personal template locally approved.
publisherReviewStatus=approvedandpublisherExecutionStatus=passedare publisher/Gallery facts. They never mean that SFL executed code or reassessed the scientific conclusion;codeExecutedBySflClientremainsfalse.
What ships with it
2 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.
- today Changed a9f55b5c9bd0
- 2d ago Changed · +16 lines 0a35ae981b9d
- 3d ago Changed · +4 lines 2c713c427941
- 4d ago Changed d5ac77cf3ca0
- 6d ago Changed · +83 lines · +4 tokens per session 24a89b2991e0
- 8d ago Changed 6da8c686bd6a
- 12d ago First seen · 543 lines · 38 tokens per session scan A 7b6b02439c43
figure-library is a skill published in the GitHub repository xuzhougeng/ScientificFigureLibrary (66 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 7,639 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
svg-editor
Open and surgically edit SVG scientific figures in the SVG Editor MCP App. Use when the user wants to change text, colors, fonts, positions, legends, or panel letters in an existing SVG by hand, or by selecting elements and instructing the host assistant.
agent-figure-gallery
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
bio-differential-expression-batch-correction
Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against…
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.