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 5.5 | $0.00092 | $0.05385 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 6mo ago), licensed MIT. It adds 231 tokens to every session and 13,462 once invoked, about $0.0009 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.
paper-figure-styling compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-figure-stylingzhousodo/paper-submission-check | Skill | 24 | 6mo ago | MIT | A | 231 | Codex |
| scientific-schematicsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 68 | Claude Code |
| paper-poster-htmlwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 107 | Claude Code |
| latex-postersforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | 3d ago | Apache-2.0 | A | 53 | Claude Code |
| paperFigWUBING2023/PaperSpine | Skill | 6.2k | 23d ago | MIT | A | 126 | Claude Code, Codex |
| figure-composercompanion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 42 | Claude Code, Codex |
| schematicssynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 134 | Claude Code |