Luxas is an open-source multi-agent research system that takes a research topic through literature searches, experiments, reviews, and LaTeX manuscript compilation. It is intended for autonomous scientific research, using separate agents to read papers, run tests, create figures, and write reports. The catalogue lists skills associated with this workflow.
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 matplotlib-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/matplotlib-figures)<a href="https://agentmods.dev/skills/muuuun/luxas/matplotlib-figures"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/matplotlib-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/matplotlib-figures"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/matplotlib-figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01574 |
| Opus 5.5 | $0.00032 | $0.00630 |
| Sonnet 5.5 | $0.00016 | $0.00315 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
matplotlib-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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matplotlib Figures Skill
Step 0 — data figures go through figspec (mandatory for agents)
python3 <luxas_root>/skills/matplotlib-figures/scripts/figspec <name>.figspec.json renders a
declarative spec (series as CSV references, one highlight, reference lines, bands) through a fixed
template that owns style, marker policy, occupancy-aware label placement and legends. Grammar:
references/figspec_schema.md. The grammar is strict (figures v4, 2026-09-05): an unknown key is an
error naming the key to use; exit 2 means the figure is not done (a label that could not be placed, more than
five series, a page-tall layout) and compile_latex reads the same findings from <pdf>.figlint.json.
Energy-level diagrams go through skills/figure/scripts/levelspec (grammar
skills/figure/references/levelspec_schema.md). The archetype/figlint workflow below remains for figure classes
the spec cannot express (dot matrices, comparison planes); a plain y(x) figure written in raw
matplotlib by an agent is a defect.
All generated figures MUST be publication-quality: load a venue-matched style, save as vector PDF, use colorblind-safe palettes.
3-step workflow
Step 1 — Set up the figure style (once per project)
When you have determined the target venue, copy BOTH the matching matplotlib style template AND the domain style guide to your project (half-upgrading only the mplstyle recreates the figstyle/guide palette divergence). Your brain prompt supplies the venue-specific directory as {{VENUE_SPECIFIC_DIR}}:
cp {{VENUE_SPECIFIC_DIR}}figstyles/<style>.mplstyle report/figstyle.mplstyle
cp <luxas_root>/skills/figure/style_guides/<domain>.md report/figures/style_guide.md
Style map:
| Venue | Style file | Notes |
|---|---|---|
| Physics (PRL, PRX, APS journals) | physics-aps.mplstyle |
CM fonts, LaTeX, 600 DPI |
| CS conferences (NeurIPS, ICML, ICLR) | cs-conferences.mplstyle |
sans-serif, 300 DPI |
| Nature / Science / Cell / PNAS | nature-science.mplstyle |
Arial, compact, 300 DPI |
| Chemistry (JACS, ACS journals) | chemistry-acs.mplstyle |
Arial, 300 DPI |
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.
- lint_hook/figlint_core.py 8.9 KB runs code
- lint_hook/figplace.py 5.2 KB runs code
- lint_hook/sitecustomize.py 3.0 KB runs code
- references/archetype_comparison.py 4.6 KB runs code
- references/archetype_matrix.py 2.3 KB runs code
- references/archetype_scan.py 2.3 KB runs code
- references/DESIGN.md 2.4 KB
- references/figspec_schema.md 11 KB
- scripts/figlint 2.7 KB
- scripts/figlint-pdf 17 KB
- scripts/figspec 54 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 Changed · +4 lines 044ef4545887
- 1mo ago First seen · 100 lines · 79 tokens per session scan A 2300ad2c8bf4
matplotlib-figures is a skill published in the GitHub repository Muuuun/luxas (1,169 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 1,574 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 2026-08-30.
Other skills, from other repositories
research-rigor
A structured method for doing research and analysis with explicit assumptions, evidence checks, scoring criteria, independent review, and later accuracy checks. The description is mainly in Chinese and does not define a specific software integration.
nature-academic-search
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv). Use when the user needs coordinated multi-step literature workflows beyond a…
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
neuroskill-bci
Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.