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 Muuuun/luxas --skill paper-figuresgit clone --depth 1 https://github.com/Muuuun/luxasWrote 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/muuuun/luxas/paper-figures)<a href="https://agentmods.dev/skills/muuuun/luxas/paper-figures"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/paper-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/muuuun/luxas/paper-figures"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/paper-figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 63 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00079 | $0.00668 |
| Opus 5 | $0.00039 | $0.00334 |
| Sonnet 5 | $0.00016 | $0.00134 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
paper-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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Figures Skill
Figures are information. A survey/review report covering downloaded papers MUST include key figures — architecture diagrams, experimental results, comparisons. Do NOT write a text-only survey when figures are available.
3-step workflow
Step 1 — Extract figures from downloaded papers
Your brain prompt supplies the script's absolute path as {{EXTRACT_FIGURES}}. Invoke it once per paper:
{{EXTRACT_FIGURES}} data/papers/<paper-id>.pdf # single PDF
{{EXTRACT_FIGURES}} data/papers/<arxiv-id> # arXiv source directory
This creates data/papers/<id>_figures/ with extracted images and a manifest.json listing each figure with caption and page number.
Step 2 — Review captions and classify every figure
Read every manifest:
cat data/papers/*_figures/manifest.json
Record your decisions in notes/memory.md under a ## Figure Review section. Every figure must end up in one of three states:
- USE — essential for understanding the topic; will be included in the report
- SKIP — irrelevant, redundant, or low quality
- UNREVIEWED — caption not yet read (only acceptable as a transient state)
Select figures that are:
- Essential for understanding the topic (architecture diagrams, system schematics)
- Key experimental results that support your narrative
- Useful comparisons across methods, systems, or time periods
- Visually informative (not just tables rendered as images)
Step 3 — Include USE figures in the report
For each figure marked USE, embed it directly in LaTeX:
\begin{figure}[t]
\centering
\includegraphics[width=\linewidth]{../data/papers/<id>_figures/<filename>}
\caption{<Your caption describing the figure in the context of your survey>. Adapted from \cite{<key>}.}
\label{fig:<label>}
\end{figure}
Rules
- Coverage: survey/review reports include at least 3-5
USEfigures from downloaded papers, in addition to any figures you generate yourself. - Captions: write your OWN caption in the context of the survey narrative — do not copy the original caption.
- Attribution: always cite the source paper with
\cite{}. - No skipping the review step: every extracted figure must be classified before writing the report.
- Complementary: you may also generate your own figures (see
skills/matplotlib-figures/SKILL.md) for data summaries, timelines, or cross-paper comparisons not found in existing figures.
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.
- 10d ago First seen · 64 lines · 79 tokens per session scan A b63f3002e4bc
paper-figures is a skill published in the GitHub repository Muuuun/luxas (1,003 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 668 once invoked, about $0.0004 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
paper-compile
A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
beamer-deck
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.
latex-polish
Inspect a cleanly compiling LaTeX document for source pathologies and rendered visual defects by linting and viewing selected PDF pages. Use when compilation succeeds but title pages, floats, tables, figures, or layout still need publication-quality review. Not for basic compilation health; use $latex-health-check.
latex-health-check
Compile all LaTeX projects and report cross-project build consistency. Use when checking whether a collection of papers builds cleanly. Not for rendered visual inspection after a clean build; use $latex-polish.
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…