ciclo-de-pesquisa

ciclo-de-pesquisa is a skill for Claude Code from nett0eth/research-stack. It costs 115 tokens per session (1,011 once invoked), scanned A, original, MIT.

A research workflow for finding trustworthy sources, checking evidence, and producing an auditable report in Markdown. It uses primary sources such as official documents and research papers before less direct sources.

In plain words
What is it for?
Use it to research a topic, verify facts, compare sources, find papers in places such as bioRxiv—a website for sharing biology research before formal publication—and write reports with citations.
Why use it?
It reduces unsupported claims, hidden disagreements between sources, and reports whose numbers or conclusions cannot be checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the research-stack plugin — 3 skills, 2 MCP servers shipped together

Good fit Use it to research a topic, verify facts, compare sources, find papers in places such as bioRxiv—a website for sharing biology research before formal publication—and write reports with citations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nett0eth/research-stack/ciclo-de-pesquisa
Install

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.

Any agent
npx skills add nett0eth/research-stack --skill ciclo-de-pesquisa
Clone the repo
git clone --depth 1 https://github.com/nett0eth/research-stack

Made for: Claude Code.

Or install research-stack, the plugin that ships this one along with the rest of its 3 skills, 2 MCP servers.

Wrote 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.

agentmods badge for ciclo-de-pesquisa

README.md
[![agentmods](https://agentmods.dev/badge/skills/nett0eth/research-stack/ciclo-de-pesquisa/github.svg)](https://agentmods.dev/skills/nett0eth/research-stack/ciclo-de-pesquisa)
Your own site
<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.

agentmods 80×15 button for ciclo-de-pesquisa

Your own site · 80×15
<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>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,011 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 02b578de4c09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/ciclo-de-pesquisa/SKILL.md · 79 lines

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.

  1. 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.
  2. 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.
  3. Amostra fraca é marcada. Padrão observado em menos de cinco casos entra como "amostra fraca", jamais como conclusão.
  4. 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.

Read the full file on GitHub · 79 lines

Changes

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.

  1. 10d ago First seen · 79 lines · 115 tokens per session scan A 02b578de4c09

Subscribe to this mod's changes

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.

Related

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.

yang3kc/daily_arxiv_digest · 66 tokens

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…

mlava/scholar-sidekick-mcp · 153 tokens

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…

aniketkrs/research-paper · 147 tokens

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…

aniketkrs/research-paper · 172 tokens

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…

aniketkrs/research-paper · 159 tokens

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.

artokun/comfyui-mcp · 68 tokens