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 | $0.00081 | $0.04023 |
| Sonnet 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 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 — 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.
- 10d ago First seen · 604 lines · 161 tokens per session scan A fc46d45c6bd7
survey-methodology is a skill published in the GitHub repository Muuuun/luxas (1,003 stars, last pushed 4d ago), licensed MIT. It adds 161 tokens to every session and 8,047 once invoked, about $0.0008 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
forecasting
Superforecasting with calibrated reasoning, Brier score tracking, and prediction ledger management.
aws-fde-delivery
Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap.
evaluate
Evaluate technologies and competitive developments against Genesis architecture.
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.
linkedin-comment-strategy
This skill should be used when the user asks to "write a comment for this LinkedIn post", "help me respond to this post", "what should I comment on this", "craft a LinkedIn comment", or when Genesis identifies high-value posts in the user's network worth engaging with. Also triggered by "how should I engage on…