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 zhousodo/paper-submission-check --skill paper-figure-stylinggit clone --depth 1 https://github.com/zhousodo/paper-submission-checkWrote 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/zhousodo/paper-submission-check/paper-figure-styling)<a href="https://agentmods.dev/skills/zhousodo/paper-submission-check/paper-figure-styling"><img src="https://agentmods.dev/badge/skills/zhousodo/paper-submission-check/paper-figure-styling/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/zhousodo/paper-submission-check/paper-figure-styling"><img src="https://agentmods.dev/badge/skills/zhousodo/paper-submission-check/paper-figure-styling.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 | $0.00231 | $0.13462 |
| Opus 5 | $0.00115 | $0.06731 |
| Sonnet 5 | $0.00046 | $0.02692 |
| Haiku 4.5 | $0.00023 | $0.01346 |
Grade A, and why
paper-figure-styling 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 — 1,124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Figure Styling & Visual Design
Systematic quality guide for all visual elements in academic papers. Applies to cybersecurity venues (S&P, CCS, USENIX Security, NDSS, TDSC, TIFS, Computers & Security) and general CS journals.
Execution Safety [CRITICAL]
Before applying style changes:
- Do not change reported values, statistical results, labels, or ranking order.
- Do not alter figure semantics to "look better" (for example, axis range tricks that hide variance).
- Keep figure/table numbering and cross-references stable unless user explicitly requests renumbering.
- Preserve reproducibility: any style adjustment should be scriptable (LaTeX/pgfplots/matplotlib config), not manual one-off edits.
Workflow
Figure Styling Progress:
- [ ] Phase 1: Color System Setup (palette + semantic mapping + fill opacity)
- [ ] Phase 2: Typography Audit (figure fonts, table fonts, sizes, math mode)
- [ ] Phase 3: Axis, Grid & Proportion System (ticks, grid, aspect ratio, data-ink)
- [ ] Phase 4: Visual Encoding System (color + line style + marker)
- [ ] Phase 5: Per-Figure-Type Review (with aspect ratio per type)
- [ ] Phase 6: Legend Design System (position, styling, shared legend, decision tree)
- [ ] Phase 7: Statistical Visualization (error bars, significance markers, CI bands)
- [ ] Phase 8: Layout, Float Placement & Page Density
- [ ] Phase 9: Table Visual Design
- [ ] Phase 10: Caption & Label Formatting
- [ ] Phase 11: Cross-Reference & Hyperlink Audit
- [ ] Phase 12: Cross-Figure Consistency Audit
- [ ] Phase 13: Export Quality Pipeline
- [ ] Phase 14: Grayscale & Accessibility Test
- [ ] Phase 15: Publisher Compliance Final Check
Phase 1: Color System
Default Palette: Okabe-Ito (Wong)
\definecolor{acBlue}{HTML}{0072B2} % proposed method / primary
\definecolor{acOrange}{HTML}{E69F00} % baseline 3
\definecolor{acGreen}{HTML}{009E73} % baseline 2 / benign class
\definecolor{acVermillion}{HTML}{D55E00} % strongest baseline / attack class
\definecolor{acPurple}{HTML}{CC79A7} % baseline 4
\definecolor{acSky}{HTML}{56B4E9} % baseline 5 / auxiliary
\definecolor{acYellow}{HTML}{F0E442} % caution: low contrast on white
\definecolor{acBlack}{HTML}{000000} % reference / oracle / axis
What ships with it
5 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.
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 · 1,124 lines · 231 tokens per session scan A 1b2b2f43e0e6
paper-figure-styling is a skill published in the GitHub repository zhousodo/paper-submission-check (24 stars, last pushed 4mo ago), licensed MIT. It adds 231 tokens to every session and 13,462 once invoked, about $0.0012 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
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…
paper-poster-html
A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.
paperFig
Design, implement, revise, and validate publication-quality scientific figures from references, existing plotting code, and real project data. Trace every figure to source code and inputs; deconstruct reference figures; plan the scientific story and multi-panel structure; build complex model architecture and…
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-composer
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
ccf-visual-composer
A visual design assistant for research papers, presentations, posters, and README graphics. It can lay out figures, tables, diagrams, icons, colors, and other visual elements, including editable SVG, PDF, and PPTX outputs.