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 ai4paper/apaper-plugin --skill creating-figuresgit clone --depth 1 https://github.com/ai4paper/apaper-pluginWrote 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/ai4paper/apaper-plugin/creating-figures)<a href="https://agentmods.dev/skills/ai4paper/apaper-plugin/creating-figures"><img src="https://agentmods.dev/badge/skills/ai4paper/apaper-plugin/creating-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/skills/ai4paper/apaper-plugin/creating-figures"><img src="https://agentmods.dev/badge/skills/ai4paper/apaper-plugin/creating-figures.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00086 | $0.02282 |
| Opus 5.5 | $0.00034 | $0.00913 |
| Sonnet 5.5 | $0.00017 | $0.00456 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
creating-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 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Scientific Figures
Create compact, print-friendly figures for academic papers. Two backends are supported, and the choice is determined by the host paper's file type — not by preference:
| Host paper | Backend |
|---|---|
LaTeX (.tex, \documentclass{...}) |
TikZ — see TIKZ.md |
Typst (.typ) |
CeTZ — see TYPST.md |
Detection rule
Before generating any figure, identify the host paper:
- Look at the working directory (or the path the user gave you) for the main paper source.
- If it ends in
.tex(or you find\documentclass/\begin{document}anywhere in the project), produce a TikZ figure. - If it ends in
.typ(or you find#set page/#import "@preview/..."anywhere in the project), produce a CeTZ figure. - If both exist, default to whichever the user is currently editing or pointed you at.
- Only ask the user if neither extension is present in the working tree.
Never mix backends: a TikZ figure cannot be included in a Typst paper (and vice versa) without first compiling to a standalone PDF/SVG.
Quick Start
LaTeX/TikZ
Minimal block diagram:
% 10pt = the host paper's base font size — copy it from the paper, don't pick your
% own. (Sizes other than 10/11/12pt are silently dropped by article; use
% class=<paperclass> instead — see TIKZ.md, Standalone Compilation.)
\documentclass[tikz,border=2mm,10pt]{standalone}
\usetikzlibrary{arrows.meta,positioning}
\begin{document}
\begin{tikzpicture}[
block/.style={rectangle, draw, fill=gray!15, minimum width=2cm, minimum height=0.8cm, font=\sffamily},
arrow/.style={->, >=Stealth, thick}
]
\node[block] (a) {Input};
\node[block, right=of a] (b) {Process};
\node[block, right=of b] (c) {Output};
\draw[arrow] (a) -- (b);
\draw[arrow] (b) -- (c);
\end{tikzpicture}
\end{document}
What ships with it
11 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/tikz/block-diagram.tex 1.8 KB
- examples/tikz/decision-workflow.tex 1.7 KB
- examples/tikz/parallel-pipeline.tex 1.7 KB
- examples/tikz/system-architecture.tex 1.7 KB
- examples/typst/block-diagram.typ 2.8 KB
- examples/typst/decision-workflow.typ 2.2 KB
- examples/typst/parallel-pipeline.typ 1.9 KB
- examples/typst/system-architecture.typ 1.9 KB
- PRINCIPLES.md 8.0 KB
- TIKZ.md 13 KB
- TYPST.md 15 KB
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 · 185 lines · 86 tokens per session scan A f0957a12cccf
creating-figures is a skill published in the GitHub repository ai4paper/apaper-plugin (4 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,282 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
latex-posters
Use when creating or revising LaTeX research posters with beamerposter, tikzposter, or baposter, including poster layout, typography, color, print sizing, figure placement, QR codes, compilation, and print-ready PDF checks.
figure-planner
Use when designing, restructuring, or auditing manuscript figures and you need to define one main claim per figure, assign panel roles, align legends with the text, or decide what belongs in main figures versus supplement.
drawio-academic-skills
Publication-figure overlay for draw.io. Use instead of drawio whenever the diagram is for a paper, thesis, dissertation, journal, conference, IEEE/ACM submission, manuscript, camera-ready, Word/LaTeX figure, or other publication. Applies venue, figure-type, color, caption/legend, formula, and paper-readability gates…
figure-drawing
A workflow for making editable draw.io diagrams for research papers, technical systems, concepts, processes, and data.
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via deriveoutlinetask(png). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → fan-out one subagent per panel (each loads figure-style) → tile + stamp letters → adversarial…
ui-first-principles
A method for deciding which information and actions should appear first in a user interface or information architecture.