figures

A plugin for creating scientific figures and diagrams, including SVG artwork, icons, labels, arrows, and scale bars. It also includes checks and export steps for figures intended for research publications.

In plain words
What is it for?
Use it to assemble publication figures, draw scientific schematics, make transparent scientific icons, add labels to AI-generated images, and prepare SVG files for editing or export.
Why use it?
It helps avoid common problems in scientific graphics, such as unreadable text, misaligned arrows, inconsistent colors, and files that are difficult to hand off to a graphics editor.

Plugin for Claude Code

Install

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.

agentmods
npx agentmods add plugins/neuromechanist/research-skills/figures
Claude Code
/plugin marketplace add neuromechanist/research-skills
Clone the repo
git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

figures 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.

plugins/figures/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "figures",
  "version": "0.11.0",
  "description": "Publication-quality figures plugin. Seven skills + one QA agent. scientific-figure: svgutils composer with pre-export font-size validation against Nature/Science/Cell/PNAS minima and Inkscape/cairosvg export. transparent-icons: flat scientific icons via Codex CLI or OpenAI Images API with Pillow-threshold or rembg/BiRefNet transparency post-process. svg-figure: hand-authored or programmatic SVG schematics with text-alignment, arrow-pattern, and palette-compliance guidelines, plus an Illustrator/Affinity editor-handoff reference and the editor_prep.py handoff pass. svg-primitives: mm-precise SVG builder in Python; auto-fits text boxes from measured font metrics, snaps arrow endpoints to box edges via svgpathtools intersection, emits <marker orient='auto'> for tangent-correct arrowheads on curves and orthogonal turns, supports straight/cubic/orthogonal-h/orthogonal-v routing plus multi-waypoint paths and rounded corners, and ships Bracket/Annotation/Group primitives. ai-full-figure: AI-generated pictorial substrate plus programmatic label/arrow/scale-bar overlay; hard-ceiling rules route complex figures back to scientific-figure or svg-figure. plot-styling: library decision tree (matplotlib / seaborn / plotnine / plotly / PyVista) with SciencePlots recipes for Nature, IEEE, Science, Cell, PNAS, APS. figure-qa agent: type-dispatching QA across SVG / raster / plot-script / composed-figure inputs with strict programmatic-vs-VLM separation.",
  "author": {
    "name": "Seyed Yahya Shirazi",
    "email": "[email protected]"
  },
  "license": "BSD-3-Clause",
  "skills": "./skills/",
  "keywords": ["figures", "publication", "svgutils", "icons", "gpt-image", "scientific", "qa", "matplotlib"]
}
Changes

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.

  1. yesterday First seen · 13 lines scan A f79f4e39c2fd

Subscribe to this mod's changes

figures is a plugin published in the GitHub repository neuromechanist/research-skills (43 stars, last pushed 2d ago), licensed BSD-3-Clause. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.