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 skills add nanoAgentTeam/research-claw --skill figure-drawinggit clone --depth 1 https://github.com/nanoAgentTeam/research-clawWrote 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/nanoagentteam/research-claw/figure-drawing)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/figure-drawing"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/figure-drawing/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/nanoagentteam/research-claw/figure-drawing"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/figure-drawing.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 | $0.00062 | $0.01185 |
| Opus 5.5 | $0.00025 | $0.00474 |
| Sonnet 5.5 | $0.00012 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
figure-drawing 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Figure Drawing
CRITICAL RULES (read first)
- NEVER inline TikZ code into paper sections. No
\begin{tikzpicture}insidesections/*.texormain.tex. - NEVER
\input{figures/xxx.tex}a raw .tex file. The paper must use\includegraphics. - Every figure = standalone .tex → compile → PDF/PNG →
\includegraphics. - Always compile and verify the standalone figure before inserting into the paper.
SOP
Step 1: Plan the figure
Before writing any code, decide:
- Type: taxonomy tree, architecture diagram, flowchart, bar/line chart, comparison table, timeline
- Content: what nodes/elements to show (read the relevant paper sections first)
- Layout direction: top-to-bottom or left-to-right (pick whichever avoids crowding)
- Estimated element count: if > 20 nodes, split into multiple figures
Step 2: Write the TikZ source
Write a standalone .tex file in figures/:
\documentclass[tikz,border=10pt]{standalone}
\usepackage[T1]{fontenc}
\usepackage{tikz}
\usetikzlibrary{positioning, arrows.meta, shapes, fit, backgrounds}
% Add other libraries as needed
\begin{document}
\begin{tikzpicture}[...]
% figure content
\end{tikzpicture}
\end{document}
Step 3: Compile to PDF, then convert to PNG
cd figures/
pdflatex -interaction=nonstopmode xxx.tex
# Convert PDF to PNG (try available tools in order)
pdftoppm -png -r 300 xxx.pdf xxx_fig # produces xxx_fig-1.png
# OR: convert xxx.pdf -density 300 xxx.png
# OR: sips -s format png xxx.pdf --out xxx.png (macOS)
If pdftoppm / convert / sips are all unavailable, keep the PDF and use
\includegraphics{figures/xxx.pdf} as fallback.
Step 4: Insert into paper
\begin{figure}[t]
\centering
\includegraphics[width=\columnwidth]{figures/xxx.png}
\caption{Descriptive caption.}
\label{fig:xxx}
\end{figure}
Step 5: Visual check
After compiling the full paper, verify the figure renders correctly and is
referenced in the text with \ref{fig:xxx}.
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.
- 1mo ago First seen · 127 lines · 62 tokens per session scan A 943822d5e9c4
figure-drawing is a skill published in the GitHub repository nanoAgentTeam/research-claw (137 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,185 once invoked, about $0.0002 per session on Opus 5.5. 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
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…
paper-length-gate
Deterministic artifact-backed manuscript readiness gate for meta-paper-write. Validates the workspace LaTeX artifact before compilation while leaving final page-count enforcement to compilepdf.
paper-plot-stub
Plot a results CSV (x, ybaseline, yours) as a two-line matplotlib chart and write a PDF. Demo-only.
latex-rescue
Diagnose and repair LaTeX build failures in local projects or supplied logs. Make minimal source fixes, preserve scientific content and reference keys, and report actual build evidence and unresolved errors.
pdf2tex
Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Preserve source evidence, flag uncertain math/tables/citations, and distinguish text extraction, OCR, reconstruction, and verified compilation.