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 nett0eth/research-stack --skill ciclo-de-pesquisagit clone --depth 1 https://github.com/nett0eth/research-stackWrote 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/nett0eth/research-stack/ciclo-de-pesquisa)<a href="https://agentmods.dev/skills/nett0eth/research-stack/ciclo-de-pesquisa"><img src="https://agentmods.dev/badge/skills/nett0eth/research-stack/ciclo-de-pesquisa/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/nett0eth/research-stack/ciclo-de-pesquisa"><img src="https://agentmods.dev/badge/skills/nett0eth/research-stack/ciclo-de-pesquisa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00115 | $0.01011 |
| Opus 5 | $0.00057 | $0.00505 |
| Sonnet 5 | $0.00023 | $0.00202 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
ciclo-de-pesquisa 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ciclo de pesquisa
Conduza a pesquisa em estações, na ordem. Não pule a ingestão nem a memória.
As quatro regras inegociáveis
Aplique em toda pesquisa, sem exceção e sem esperar o usuário pedir.
- Fonte primária na frente. Ordem de confiança: documentação oficial e repositório do projeto, depois publicação primária ou paper, depois análise de terceiro, e por último blog agregador, que serve apenas como pista para confirmar em outro lugar. Nunca encerre em blog agregador.
- Divergência é reportada, nunca resolvida em silêncio. Quando duas fontes discordam, apresente as duas com a data de cada uma e diga qual é a primária. Escolher a mais conveniente sem avisar é falha grave.
- Amostra fraca é marcada. Padrão observado em menos de cinco casos entra como "amostra fraca", jamais como conclusão.
- Saída auditável. Todo número, valor monetário ou superlativo carrega a URL e a data de acesso ao lado. Sem isso, o dado não sai do rascunho.
Estação 1: fonte primária
Use o MCP paper-search para localizar literatura em arXiv, PubMed, bioRxiv, Semantic Scholar, Crossref, OpenAlex e Unpaywall.
Peça sempre o DOI junto do título, porque o DOI sobrevive a link quebrado. Baixe os PDFs numa pasta ./fontes do projeto.
Quando o tema for tecnologia ou produto em vez de ciência, a fonte primária é o repositório, a documentação oficial e o changelog. Contagem de stars, versão e data de release devem ser lidas na página do projeto, nunca em artigo que cita o projeto.
Estação 2: ingestão legível
Antes de ler qualquer documento, converta. Delegue para a skill ingestao, que roteia cada tipo de arquivo para o conversor certo.
Nunca analise um PDF de duas colunas sem converter antes. Ordem de leitura embaralhada gera conclusão embaralhada.
Estação 3: protocolo
Antes de investigar, escreva no arquivo de saída:
- a pergunta exata, em uma frase
- o critério que decide a resposta, fixado agora e não depois
- o que falsificaria a hipótese
Se o usuário instalou o RigorPilot, delegue a execução para ele quando o trabalho for reprodução de experimento.
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 · 79 lines · 115 tokens per session scan A 02b578de4c09
ciclo-de-pesquisa is a skill published in the GitHub repository nett0eth/research-stack (4 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,011 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
arxiv-fetch
Fetch the latest arXiv papers and generate an on-demand digest. Use when the user asks to fetch/check today's (or the latest) arXiv papers, find new papers on a topic, or generate an ad-hoc arXiv digest. The agent judges relevance itself — no API keys needed.
scholar-sidekick
This skill should be used when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, or verification that a claimed citation is real (not…
research-paper
Enterprise-grade autonomous research paper generation skill for AI coding agents — full papers, literature reviews, theses, whitepapers, surveys, policy briefs — with rigorous methodology, statistical validation, multi-style citations (Harvard / APA / IEEE / MLA / Chicago / Nature / arXiv-numeric), and rich…
read-research-paper
Renders ANY research paper (URL / arXiv ID / DOI / PDF / pasted text) into a visually engaging multi-format reading experience — with mind maps, method flowcharts, key-finding infographics, comparison tables, related-work timelines, and a plain-English layer alongside the technical content. Activates on slash commands…
get-research-paper
Discovers, retrieves, ranks, and summarizes real existing research papers on any topic. Searches arXiv, Google Scholar, PubMed, Semantic Scholar, and reputable open repositories; returns a curated reading list with verified DOIs, key findings, and citation-ready metadata. Activates on slash commands…
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.