Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/neuromechanist/research-skillsnpx agentmods add skills/neuromechanist/research-skills/svg-primitivesWrote 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/neuromechanist/research-skills/svg-primitives)<a href="https://agentmods.dev/skills/neuromechanist/research-skills/svg-primitives"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/svg-primitives/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/neuromechanist/research-skills/svg-primitives"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/svg-primitives.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.03871 |
| Opus 5 | $0.00063 | $0.01936 |
| Sonnet 5 | $0.00025 | $0.00774 |
| Haiku 4.5 | $0.00013 | $0.00387 |
Grade A, and why
svg-primitives 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 12d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SVG Primitives
Build mm-precise SVG schematics in Python with three mechanical guarantees:
- Text never overflows its container — labeled shapes auto-size to fit measured text bbox + padding.
- Arrowheads stay tangent-correct — arrows emit
<marker orient="auto">so the renderer rotates the head along the path's terminal tangent; works on straight lines and cubic Beziers. - Paint order is deterministic — layers paint in registration order; connectors visibly pass under boxes without manual reordering.
The skill ships an end-to-end pytest suite (50+ tests) that renders SVGs and asserts these invariants on the rendered output, so the guarantees are enforced by construction rather than by hand-checking each figure.
When to use this skill
Reach for svg-primitives when:
- The figure is a schematic (boxes, arrows, labels) and you're driving it from Python — e.g. nodes come from a YAML config, or the layout depends on data.
- You need the boxes to auto-fit their labels (no hand-tuning widths).
- The figure has curved arrows that must point cleanly at their targets.
- You want deterministic z-order so connectors sit under shapes without manual element reordering.
- The output will be composed into a multi-panel figure as a panel SVG that
scientific-figure/compose.pyloads.
Reach for a different tool when:
- The figure is plotted from numbers (matplotlib/seaborn/plotnine) → use
[[plot-styling]]. - The figure is a photographic / pictorial substrate (a brain scene, microscope setup) → use
[[ai-full-figure]]for the substrate and overlay labels via Arrow/LabeledBox here. - The figure is hand-authored SVG or the patterns are reference material for hand-authoring → use
[[svg-figure]](this skill's library-agnostic counterpart).
Quick start
from svg_primitives import Canvas, LabeledBox, Arrow
c = Canvas(width_mm=183, height_mm=80)
boxes = c.layer("boxes")
arrows = c.layer("connectors")
raw = boxes.add(LabeledBox(x=10, y=20, text="Raw EEG", font_size=7))
band = boxes.add(LabeledBox.next_to(raw, side="E", gap=10, text="Bandpass\nfilter", font_size=7))
ica = boxes.add(LabeledBox.next_to(band, side="E", gap=10, text="Independent component\nanalysis", font_size=7))
arrows.add(Arrow.connect(raw, band)) # straight, snapped to edges
arrows.add(Arrow.connect(band, ica)) # straight
arrows.add(Arrow.connect(ica, raw, curve="cubic", bow=14, # feedback arc
stroke="#C45146")) # red — gets its own red marker
c.save("eeg.svg", output_png=True)
What ships with it
22 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.
- examples/.gitignore 5 B
- examples/bracketed_grouping.py 2.8 KB runs code
- examples/eeg_pipeline.py 3.0 KB runs code
- examples/orthogonal_flowchart.py 2.2 KB runs code
- examples/stress_test.py 2.6 KB runs code
- examples/validation_demo.py 2.6 KB runs code
- references/api.md 11 KB
- references/design.md 6.3 KB
- references/font-metrics.md 4.5 KB
- scripts/.gitignore 13 B
- scripts/svg_primitives/__init__.py 2.0 KB runs code
- scripts/svg_primitives/annotations.py 8.0 KB runs code
- scripts/svg_primitives/arrows.py 9.6 KB runs code
- scripts/svg_primitives/canvas.py 9.0 KB runs code
- scripts/svg_primitives/geometry.py 2.0 KB runs code
- scripts/svg_primitives/groups.py 3.4 KB runs code
- scripts/svg_primitives/metrics.py 7.8 KB runs code
- scripts/svg_primitives/shapes.py 10.0 KB runs code
- scripts/svg_primitives/validation.py 17 KB runs code
- tests/.gitignore 28 B
- tests/conftest.py 4.2 KB runs code
- tests/test_e2e.py 41 KB runs code
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.
- 12d ago First seen · 258 lines · 126 tokens per session scan A 0284fbc08b48
svg-primitives is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 126 tokens to every session and 3,871 once invoked, about $0.0006 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
figma-implement-design
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a…