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 survey-methodologygit 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/survey-methodology)<a href="https://agentmods.dev/skills/muuuun/luxas/survey-methodology"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/survey-methodology/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/survey-methodology"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/survey-methodology.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 | $0.00161 | $0.08047 |
| Opus 5.5 | $0.00064 | $0.03219 |
| Sonnet 5.5 | $0.00032 | $0.01609 |
| Haiku 4.5 | $0.00016 | $0.00805 |
Grade A, and why
survey-methodology 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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survey Methodology Skill
The default failure mode of an autonomous-agent survey is paper-trust: read N papers, organize claims into a taxonomy, ship a prose digest. The output passes type-check (it looks like a survey) but fails verification (none of the cited numbers checked, contradictions not adjudicated, code not opened, negative space not bounded). This produces B-grade output.
Across ~240 reviews from 2024-2026, A-grade reviews share one structural discriminator:
Removing the new taxonomy from an A-grade survey leaves a contribution. Removing it from a B-grade survey leaves nothing.
Empirical A-rate by domain (with our wave-1 + wave-2 evidence base):
| Domain | A-rate | Modal A-pattern |
|---|---|---|
| Math (Acta Numerica / Bull AMS / SIAM Review / Probab Surv) | ~86% | Re-derivation in unified notation; new short proofs |
| Economics (JEL / Annu Rev Econ / Handbook) | ~80% | Author re-estimation on harmonized data; "stylized-fact tables" |
| Engineering (Annu Rev Control/BME, PECS, ARHT) | ~73% | Author re-simulation; harmonized device spec sheets |
| Physics (RMP / Living Reviews / Annu Rev Cond Matt) | ~70% | Re-derivation + cross-paper number table; per-edition updates |
| Chemistry/materials (Chem Rev / Chem Soc Rev / Annu Rev Phys Chem) | ~60% | Cross-paper benchmark table; Tutorial Review structured-closing |
| Earth/environment (Rev Geophys / Annu Rev Earth Planet Sci / NRE&E) | ~40% | Narrative-with-embedded-re-analysis of observational data |
| CS/ML/AI surveys (arXiv survey papers) | ~13% | Bounded corpus + author benchmarks (BetterBench template) |
| Biology narrative (Nature Reviews / Annu Rev Bio / Cell / Trends) | ~7% | Almost never — venue norm is conceptual synthesis |
Cochrane / BMJ / Lancet SRs are 100% PRISMA-compliant by editorial policy but item-level adherence is asymmetric: ~75% of Cochrane abstracts use GRADE, but only ~7.5% of nominally compliant SRs across journals do full certainty + reporting-bias assessment. The PRISMA label is not the substance — verify item-by-item.
Two key empirical insights from the corpus:
-
A-grade is topic-determined, not author-determined. Surveys of open artifacts (open-source models, public conference proceedings, public datasets) admit A-grade execution. Surveys of capabilities reported by closed systems (RLHF/alignment, frontier-model agents, healthcare LLMs, industry-disclosed tools like Aletheia) are structurally trapped at B because the survey author cannot independently re-execute cited results.
-
Disagreement-handling is a near-universal blind spot. 0/31 CS surveys, ~12/30 biology reviews and ~9/30 physics reviews fence-sit on contradictions. Even A-grade work routinely fails this dimension. It is the cleanest novelty axis the agent can exploit.
What ships with it
19 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.
- references/anchor_exemplars.md 8.5 KB
- references/empirical_evidence/bio_med.md 21 KB
- references/empirical_evidence/cs_ml_math.md 19 KB
- references/empirical_evidence/interdisciplinary_protocols.md 20 KB
- references/empirical_evidence/physics_chem.md 20 KB
- references/empirical_evidence/wave2_biology_broad.md 32 KB
- references/empirical_evidence/wave2_chem_materials.md 34 KB
- references/empirical_evidence/wave2_cs_ml_broad.md 27 KB
- references/empirical_evidence/wave2_earth_med.md 33 KB
- references/empirical_evidence/wave2_math_stats.md 29 KB
- references/empirical_evidence/wave2_physics_broad.md 34 KB
- references/empirical_evidence/wave2_social_eng.md 33 KB
- references/prisma_protocols_distilled.md 9.5 KB
- references/venue_policies.md 9.5 KB
- templates/adjudication.md 4.2 KB
- templates/datasets.md 2.0 KB
- templates/excluded.md 3.7 KB
- templates/literature_entry.md 5.2 KB
- templates/scope.md 3.1 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 · 604 lines · 161 tokens per session scan A fc46d45c6bd7
survey-methodology is a skill published in the GitHub repository Muuuun/luxas (1,169 stars, last pushed 5d ago), licensed MIT. It adds 161 tokens to every session and 8,047 once invoked, about $0.0006 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.
integrate-module
Turn any external program into a Genesis module via structured discovery, connection mapping, config generation, and verification.
osint
OSINT investigation — discover, track, and report on people, companies, and technologies.
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.