A figure generator for research data using preset styles for IEEE, ACM, NeurIPS, or color-blind-safe charts. It reads JSON data and writes PDF or PNG plots.

Use it to make line, bar, or box plots for papers and camera-ready reports, with a selected publication style and output format.

It applies consistent publication-oriented layout settings instead of requiring manual chart styling for each figure. If the plotting library is unavailable, it reports a mock result rather than producing an image.

pub-plotter — Skill for Claude Code and Codex by Morningstar202604

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Morningstar202604/awesome-skillkit

agentmods

npx agentmods add skills/morningstar202604/awesome-skillkit/pub-plotter

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/pub-plotter/github.svg)](https://agentmods.dev/skills/morningstar202604/awesome-skillkit/pub-plotter)

Your own site

<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/pub-plotter"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/pub-plotter/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/pub-plotter"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/pub-plotter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,545 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00151	$0.02545
Opus 5.5	$0.00060	$0.01018
Sonnet 5.5	$0.00030	$0.00509
Haiku 4.5	$0.00015	$0.00254

Measured 1mo ago against content hash 795d4cae76eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pub-plotter 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.

site/skills/paper/pub-plotter/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publication Plotter

One-click produce publication-grade figures from a data JSON: real journal physical widths + Type-42 font embedding + colorblind-safe palette by default, no hand-tuning rcParams; if the scienceplots package is installed it automatically uses the official style.

This skill is the paper domain's single plotting entry (line / bar / boxplot / heatmap).

Honest disclosure (two tracks): matplotlib installed -> status:"success", rendered:true, the artifact is a real PDF/PNG (with embedded fonts); not installed -> it doesn't error but reports status:"mock", no image produced, and you MUST tell the user no figure was generated; don't pass the JSON report as the deliverable.

Publication-Grade Key Points (Why Plots Are Made This Way)

Font embedding: pdf.fonttype=42 / ps.fonttype=42 (Type 42 subset embedding); arXiv / LaTeX won't reject it, and it stays sharp when scaled.
Plot to the layout: --journal nature_single|science|ieee|acm|neurips uses real physical widths (Nature single column 3.504"~89mm, Science 4.76", IEEE 3.5"); "design to final size" avoids text being too big/small after inserting back into the layout.
Width contract (a silent bug fixed): --style only controls font size/line width/grid, --journal only controls physical width; the two are separated and both explicitly report width_inches. The old version stuffed the journal name into --style for lookup, and nature_single/science weren't in the table -> silently fell back to IEEE 3.5" width while still reporting success. Now an unknown --journal exits with code 2; --style science also has its own 4.76" geometry, no longer borrowing ieee. How to verify: read the produced PDF's /MediaBox; --journal science must be visibly wider than --journal ieee.
Colorblind-safe: Paul Tol / Okabe-Ito palettes on by default (--no-colorblind to turn off) — a hard review criterion for paper color choices.
Vector output: .pdf vector (recommended for submission), .png 300 dpi as fallback.

Read the full file on GitHub · 114 lines

Changes

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 Changed · -1 lines · -33 tokens per session 795d4cae76eb
1mo ago Changed · +15 lines · +72 tokens per session 853fc12786ac
1mo ago First seen · 100 lines · 112 tokens per session scan A db275a6a3c00

Subscribe to this mod's changes

pub-plotter is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 2,545 once invoked, about $0.0006 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 2026-09-19.

Design and UX LLM Scientific agent-skills ai ai-agents automation content-publishing

schematics

Creates or refines publication-quality technical diagrams with the native generateimage tool (Nano Banana Pro through Ace or a Gemini key, GPT Image 2 through an OpenAI key), method and architecture overviews, pipelines, CONSORT and PRISMA flows, experimental workflows, biological pathways, circuits and conceptual…

synthetic-sciences/openscience · 134 tokens

latex-posters

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

beita6969/ScienceClaw · 60 tokens

paperbanana-diagram

Author publication-quality diagram specifications (method.txt files) from paper prose and draw.io sketches, following federal data visualization standards and Tufte design principles. Use when creating, modifying, or regenerating conceptual diagrams, architecture figures, or visual explanations for academic papers or…

brockwebb/open-census-mcp-server · 156 tokens

pub-plotter