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 venue-specificgit 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/venue-specific)<a href="https://agentmods.dev/skills/muuuun/luxas/venue-specific"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/venue-specific/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/venue-specific"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/venue-specific.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 | $0.00065 | $0.01965 |
| Opus 5.5 | $0.00026 | $0.00786 |
| Sonnet 5.5 | $0.00013 | $0.00393 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
venue-specific 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venue-Specific Formatting Skill
Know the exact rules before you write. This skill provides concrete, actionable formatting specifications for 30+ top journals and conferences across all disciplines.
When to Use
- User specifies a target journal or conference for their paper
- Formatting or checking a manuscript before submission
- Converting a paper from one venue's format to another
- Answering questions about a specific venue's requirements (page limits, figure specs, etc.)
How to Use
- Identify the target venue from the user's request
- Load the venue file from
references/— read ONLY the relevant file, not all of them - Load the matching writing-style file — see Writing Style Map below
- Apply rules to the current manuscript
- If venue is not covered, use
references/INDEX.mdto find the closest match + tell user to check the official author guidelines
Writing Style Map
Always load writing-style/universal.md (Gopen-Swan principles, precision, flow).
Then load the discipline-specific style guide:
| Target Venue | Also Load |
|---|---|
| NeurIPS, ICML, ICLR, AAAI, COLM, ACL | writing-style/ml-ai-conferences.md |
| OSDI, NSDI, ASPLOS, SOSP | writing-style/systems-conferences.md |
| Nature, Science, Cell, PNAS, eLife, Nature sub-journals | writing-style/high-impact-journals.md |
| Physics (PRL, PRX, Nature Physics) | writing-style/high-impact-journals.md (if broad journal) |
| Chemistry (JACS, Angewandte, Adv. Mater.) | writing-style/universal.md only |
| Biomedical (NEJM, Lancet, JAMA) | writing-style/high-impact-journals.md |
| CVPR, ICCV, ECCV | writing-style/ml-ai-conferences.md |
The venue file gives formatting rules (what). The writing-style file gives writing advice (how).
Reference Map
Load on demand. Never preload all files.
Life Sciences (Top Journals)
| File | Venue | When to Read |
|---|---|---|
life-sciences/nature.md |
Nature | Target is Nature or Nature-branded journal |
life-sciences/science.md |
Science (AAAS) | Target is Science |
life-sciences/cell.md |
Cell (Cell Press) | Target is Cell or Cell Press journal |
life-sciences/pnas.md |
PNAS | Target is PNAS |
life-sciences/elife.md |
eLife | Target is eLife |
What ships with it
60 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.
- figstyles/chemistry-acs.mplstyle 1.8 KB
- figstyles/cs-conferences.mplstyle 1.6 KB
- figstyles/general.mplstyle 2.4 KB
- figstyles/nature-science.mplstyle 1.8 KB
- figstyles/physics-aps.mplstyle 2.1 KB
- figstyles/README.md 1.2 KB
- references/biomedical/jama.md 2.8 KB
- references/biomedical/lancet.md 2.6 KB
- references/biomedical/nejm.md 2.6 KB
- references/CHECKLIST.md 3.4 KB
- references/chemistry/advanced-materials.md 2.4 KB
- references/chemistry/angewandte.md 2.3 KB
- references/chemistry/jacs.md 2.4 KB
- references/chemistry/nature-chemistry.md 2.8 KB
- references/CONVERSION.md 2.2 KB
- references/cs-conferences/aaai.md 911 B
- references/cs-conferences/acl.md 1.6 KB
- references/cs-conferences/cvpr.md 1.1 KB
- references/cs-conferences/iclr.md 878 B
- references/cs-conferences/icml.md 988 B
- references/cs-conferences/neurips.md 1.5 KB
- references/INDEX.md 2.6 KB
- references/life-sciences/cell.md 4.4 KB
- references/life-sciences/elife.md 2.6 KB
- references/life-sciences/nature.md 4.8 KB
- references/life-sciences/pnas.md 2.2 KB
- references/life-sciences/science.md 3.8 KB
- references/physics/nature-physics.md 1.9 KB
- references/physics/prl.md 6.6 KB
- references/physics/prx.md 3.7 KB
- references/publishers/acm.md 4.1 KB
- references/publishers/acs.md 3.5 KB
- references/publishers/aps.md 4.4 KB
- references/publishers/elsevier.md 3.7 KB
- references/publishers/ieee.md 3.9 KB
- references/publishers/nature-portfolio.md 3.8 KB
- references/publishers/springer.md 2.6 KB
- references/publishers/wiley.md 2.0 KB
- references/writing-style/high-impact-journals.md 5.7 KB
- references/writing-style/ml-ai-conferences.md 7.2 KB
- references/writing-style/systems-conferences.md 3.7 KB
- references/writing-style/universal.md 6.6 KB
- templates/aaai2026/aaai2026-unified-supp.tex 4.4 KB
- templates/aaai2026/aaai2026-unified-template.tex 62 KB
- templates/aaai2026/aaai2026.bib 4.7 KB
- templates/aaai2026/aaai2026.bst 29 KB
- templates/aaai2026/aaai2026.sty 12 KB
- templates/aaai2026/README.md 18 KB
- templates/acl/acl_latex.tex 14 KB
- templates/acl/acl_lualatex.tex 3.0 KB
- templates/acl/acl_natbib.bst 44 KB
- templates/acl/acl.sty 11 KB
- templates/acl/anthology.bib.txt 1.1 KB
- templates/acl/custom.bib 2.0 KB
- templates/acl/formatting.md 18 KB
- templates/acl/README.md 2.1 KB
- templates/asplos2027/main.tex 15 KB
- templates/asplos2027/references.bib 5.1 KB
- templates/colm2025/colm2025_conference.bib 496 B
- templates/colm2025/colm2025_conference.bst 26 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 First seen · 196 lines · 65 tokens per session scan A 5ad854d5bca4
venue-specific is a skill published in the GitHub repository Muuuun/luxas (1,169 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 1,965 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
evaluate
Evaluate technologies and competitive developments against Genesis architecture.
forecasting
Superforecasting with calibrated reasoning, Brier score tracking, and prediction ledger management.
user_evaluate
Evaluate content for personal relevance to the user using the user model.
aws-fde-delivery
Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap.
integrate-module
Turn any external program into a Genesis module via structured discovery, connection mapping, config generation, and verification.
lead-generation
Prospect discovery, enrichment, scoring, and reporting against an Ideal Customer Profile.