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/neuromechanist/research-skillsWrote 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/plugins/neuromechanist/research-skills/figures)<a href="https://agentmods.dev/plugins/neuromechanist/research-skills/figures"><img src="https://agentmods.dev/badge/plugins/neuromechanist/research-skills/figures/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/plugins/neuromechanist/research-skills/figures"><img src="https://agentmods.dev/badge/plugins/neuromechanist/research-skills/figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 25d 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.
What it actually says
{
"name": "figures",
"version": "0.13.0",
"description": "Publication-quality figures plugin. Eight skills + one QA agent. figure-bible: scaffolds and validates the per-project theme.json (palette, typography, text limits, Codex model settings) that every other skill reads. ai-full-figure: gpt-image-2 through the Codex CLI (or the OpenAI Images API) renders single panels or whole multi-panel figures with large verbatim titles and panel letters, panels generated in parallel with reference-image consistency, composed at journal width; a text ladder routes dense labels to the SVG overlay and numerals to plot or vector skills. transparent-icons: flat scientific icons with native alpha through the same shared backend, with an explicit Atlas Cloud path. scientific-figure: svgutils composer with pre-export font-size validation and Inkscape/cairosvg export. svg-primitives: mm-precise SVG builder with auto-fit text, edge-snapped arrows, and layer ordering; svg-figure: hand-authoring conventions and editor handoff. plot-styling: library decision tree with SciencePlots recipes. figure-qa agent: type-dispatching QA with OCR of expected strings, palette compliance against the theme, geometry and font checks, a VLM rubric, and a JSON verdict that drives the generate, QA, fix loop.",
"author": {
"name": "Seyed Yahya Shirazi",
"email": "[email protected]"
},
"license": "BSD-3-Clause",
"skills": "./skills/",
"keywords": [
"figures",
"publication",
"svgutils",
"icons",
"gpt-image",
"scientific",
"qa",
"matplotlib",
"codex",
"theme"
]
}
What it installs
The manifest is a name and a version. 8 skills, 1 agent travel with it, and installing the plugin installs all of them — 1,269 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 25d ago Changed · +11 lines 1576a0b5cf6f
- 1mo ago First seen · 13 lines scan A f79f4e39c2fd
figures is a plugin published in the GitHub repository neuromechanist/research-skills (48 stars, last pushed today), 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.
Other plugins, from other repositories
ui-ux-pro-max
UI/UX design intelligence. Searchable local database with 79 styles, 192 palettes, 74 font pairings, 25 charts, and 22 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP…
code-diagram
Analyzes source code and generates Mermaid diagrams — class, sequence, component, and architecture. Supports Dart, TypeScript, Python, Java, Kotlin, Go, Swift, Rust.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.