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 searchgit 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/search)<a href="https://agentmods.dev/skills/muuuun/luxas/search"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/search/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/search"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/search.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 | $0.00000 | $0.02363 |
| Opus 5.5 | $0.00000 | $0.00945 |
| Sonnet 5.5 | $0.00000 | $0.00473 |
| Haiku 4.5 | $0.00000 | $0.00236 |
Grade A, and why
search 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Skill
All information gathering in one place. Two CLI tools:
scripts/search— paper search, citations, download, LaTeX source, BibTeX, web search, URL fetchscripts/browse— browser automation wrapper (uses browser-use with headed + Chrome profile defaults)
Setup
bash scripts/setup.sh
scripts/search
Paper Search
scripts/search papers "Rydberg atom quantum gate"
scripts/search papers "topological insulators" --source openalex --count 20
scripts/search papers "diffusion models" --source arxiv --count 15
scripts/search papers "air pollution health effects" --source crossref --count 20
scripts/search papers "quantum error correction" --from-year 2024 --sort date --count 20
# Author-filtered search: use last name as an indexed field, not free text.
# At least one of <query> or --author is required; both together = AND.
scripts/search papers "" --author "Lukin" --from-year 2025 --sort date --count 20
scripts/search papers "neutral atom arrays" --author "Bluvstein" --count 15
- OpenAlex: all fields, citation counts, DOIs.
--source openalex - arXiv: recent preprints, physics/CS/math.
--source arxiv - CrossRef: broadest coverage (120M+ records), all disciplines, non-English journals.
--source crossref - Default: all three.
--author <LastName>: Filter by author last name. Maps to arXivau:, OpenAlexraw_author_name.search, and CrossRefquery.author— all indexed fields. Strongly preferred over putting the name in the free-text query, which treats the name as an unweighted keyword and routinely misses the target. Pair with--from-yearfor recent work by a specific researcher.--from-year YYYY: Only return papers published in YYYY or later.--sort relevance|date: Sort by relevance (default) or publication date (newest first).
Citation Chains
scripts/search citations W2057883617
scripts/search citations "10.1038/s41586-021-03819-2" --direction citations --limit 30
scripts/search citations 2301.07041 --direction references
What ships with it
7 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.
- 1mo ago First seen · 197 lines · 0 tokens per session scan A ed25bd7fe443
search is a skill published in the GitHub repository Muuuun/luxas (1,169 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,363 tokens. 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
webapp-testing
To test local web applications, write native Python Playwright scripts.
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.
adhx
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…