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/architectds/mathgraphs-mcp/openclawnpx skills add architectds/mathgraphs-mcp --skill openclawgit clone --depth 1 https://github.com/architectds/mathgraphs-mcpWrote 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/architectds/mathgraphs-mcp/openclaw)<a href="https://agentmods.dev/skills/architectds/mathgraphs-mcp/openclaw"><img src="https://agentmods.dev/badge/skills/architectds/mathgraphs-mcp/openclaw.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 | $0.00019 | $0.01318 |
| Opus 5 | $0.00010 | $0.00659 |
| Sonnet 5 | $0.00004 | $0.00264 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
mathgraphs 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Math & 3D Graphing Engine
You have access to an interactive math and 3D graphing engine via MCP. It computes and renders results — roots, extrema, intersections, and 3D scenes — on interactive graphs. Saves ~410 tokens per render vs LLM-generated canvas code.
When to use this skill
- User asks to graph, plot, or visualize any math
- User needs to verify a mathematical result visually
- You computed an answer and want to show it, not just describe it
- Geometry needs precise rendering (triangles, circles, constructions)
- User wants to build 3D scenes — shapes, architecture, creative builds with lighting and particle effects
Tools
plot_graph — Math Visualization
Plot functions, points, segments, labels, and shapes. Auto-computes roots, extrema, and intersections.
Element types:
function: expression like "x^2-4", "sin(x)", "x^2+y^2=1", "(cos(t),sin(t))"points: array of {x, y} coordinates with optional labelsegment: line from (x1,y1) to (x2,y2) with optional arrow/dashedlabel: text at position (x, y)triangle: three vertices (x1,y1,x2,y2,x3,y3)box: edge + height for bar chartscircle: center (cx,cy) + radius
Set viewport ({xmin, xmax, ymin, ymax}) to your data's magnitude — omit it and the server auto-fits the window to the elements.
Iterate with base_render_id (+ remove_indices) rather than re-sending every element. Each result reports what actually rendered, so act on any graph check it returns.
analyze — Precise Numerical Results
Compute exact values instead of doing the arithmetic yourself: roots, extrema, inflections, intersect, tangent, normal, derivative, integral, area_between, arc_length, closest_point.
Input: type (required), f (required), plus g (second expression, for intersect/area_between), x (point of interest, for tangent/normal/derivative), a/b (range, default -10..10), px/py (for closest_point).
Works with explicit, parametric, polar, and implicit curves.
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.
- 2d ago First seen · 100 lines · 19 tokens per session scan A cdeac2d173d7
mathgraphs is a skill published in the GitHub repository architectds/mathgraphs-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 19 tokens to every session and 1,318 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
Spatial Omics Skills Index
Skills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and related spatial workflows.
fin-viz-launch
Skill "fin-viz-launch" from csmar432/finai-research, covering fin-viz-launch, 触发条件, 三种工作模式, 模式一:快速模式 (quick mode) and 关键词 → 预设映射.
mayavi-3d-viz
Use this Skill for 3D scientific visualization with Mayavi: vector fields, isosurfaces, volume rendering, and animated 3D plots for physics data.
unreal-mcp
Automate Unreal Engine editor scenes, actors, and renders.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
Atrium Desktop — driving apps
Drive the user's Atrium desktop: open files in installed viewer apps (Viv bioimages, Vitessce/Spatial 3D omics, Mol structures, IGV/Gosling genomics, Volume 3D, Cytoscape, MSA, PhyloTree, RDKit), read and steer ANY window — including ones the user opened — and call app backends.