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.
/plugin marketplace add Mapika/nice-figuresnpx agentmods add plugins/mapika/nice-figures/marketplacegit clone --depth 1 https://github.com/Mapika/nice-figuresGrade A, and why
nice-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.
What it actually says
{
"name": "nice-figures",
"owner": {
"name": "Mark Marosi",
"email": "[email protected]"
},
"metadata": {
"description": "Soft-pastel, research-blog-style matplotlib figures for Claude Code.",
"version": "1.1.0"
},
"plugins": [
{
"name": "nice-figures",
"source": "./plugins/nice-figures",
"description": "Generate matplotlib figures in a soft-pastel, warm-earth, research-blog visual register — bold display titles, smoothed trends with shaded bands, rounded bars, minimal axes. Conference-ready white background by default.",
"version": "1.1.0",
"author": {
"name": "Mark Marosi",
"email": "[email protected]"
},
"homepage": "https://github.com/Mapika/nice-figures",
"repository": "https://github.com/Mapika/nice-figures",
"license": "MIT",
"category": "data-visualization",
"keywords": [
"matplotlib",
"figures",
"charts",
"data-visualization",
"research",
"soft-pastel",
"conference",
"poster",
"plotting",
"ai-agents",
"scientific-plots"
]
}
]
}
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 · 41 lines scan A f72584ed72ad
nice-figures is a plugin published in the GitHub repository Mapika/nice-figures (10 stars, last pushed 2mo ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
nveil
NVEIL is an AI-powered data-processing and visualization toolkit — describe joins, aggregations, pivots, resampling, geocoding, time-series analysis, feature engineering, 2D/3D charts, geospatial maps, voxel/volume rendering, medical imaging, and more in plain language; the toolkit plans remotely and executes entirely.
nveil
NVEIL is an AI-powered data-processing and visualization toolkit — describe joins, aggregations, pivots, resampling, geocoding, time-series analysis, feature engineering, 2D/3D charts, geospatial maps, voxel/volume rendering, medical imaging, and more in plain language; the toolkit plans remotely and executes entirely.
figure-library
Search Local Published, bundled Community, FigureYa, and explicitly trusted personal Providers, then govern immutable figure references and staged publication.
andyed-muriel
Andy Edmonds' Claude Code plugins.
reimagine-it
Claude Code plugin marketplace for /reimagine-it. Redesigns existing HTML from its own content. 15 visual directions, standalone offline pages. CLI + agent skill.
reimagine-it
Redesigns existing HTML from its own content. 15 visual directions, standalone offline pages. CLI + agent skill.