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 ingestaogit 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/ingestao)<a href="https://agentmods.dev/skills/nett0eth/research-stack/ingestao"><img src="https://agentmods.dev/badge/skills/nett0eth/research-stack/ingestao/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/ingestao"><img src="https://agentmods.dev/badge/skills/nett0eth/research-stack/ingestao.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 | $0.00086 | $0.00470 |
| Opus 5.5 | $0.00034 | $0.00188 |
| Sonnet 5.5 | $0.00017 | $0.00094 |
| Haiku 4.5 | $0.00009 | $0.00047 |
Grade A, and why
ingestao 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.
What it actually says
Ingestão
Converta antes de ler. Material que entra destruído produz conclusão destruída, e o modelo não avisa quando isso acontece.
Roteamento por tipo
| Situação | Ferramenta | Comando |
|---|---|---|
| documento comum: pdf simples, word, excel, powerpoint, epub, imagem, áudio, zip | markitdown | markitdown entrada.pdf > saida.md |
| pdf científico, duas colunas, escaneado, com fórmula ou tabela complexa | MinerU | ver README do projeto |
| conversão como etapa de pipeline automatizado | docling | ver README do projeto |
| repositório de código inteiro | repomix | ver README do projeto |
Regra de decisão em duas linhas: comece pelo markitdown, que resolve a maioria. Se a saída vier com ordem de leitura embaralhada, fórmula perdida ou tabela virada em linha corrida, o problema é layout e a resposta é MinerU.
Procedimento
- Identifique o tipo e escolha a ferramenta pela tabela
- Converta para uma pasta
./fontes-mdmantendo o nome original do arquivo - Abra a saída e verifique quatro coisas antes de seguir: os headings sobreviveram, as tabelas continuam tabelas, a ordem de leitura faz sentido, e as notas de rodapé não invadiram o corpo
- Se qualquer uma falhar, troque de conversor antes de analisar
Verificação obrigatória
Nunca declare a ingestão concluída sem abrir o markdown gerado. Conversão silenciosamente errada é a causa mais comum de análise errada, e é invisível se você confiar no processo sem olhar.
Ao relatar para o usuário, diga qual conversor foi usado e o que foi verificado.
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 · 33 lines · 86 tokens per session scan A 592cf72dd04b
ingestao is a skill published in the GitHub repository nett0eth/research-stack (4 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 470 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
markitdown
Konwersja dowolnego dokumentu (PDF, Word, Excel, PowerPoint, HTML, EPUB, audio, obrazy, YouTube) na Markdown dla LLM. Użyj gdy użytkownik mówi "konwertuj PDF", "przerób Word na markdown", "zamień PPT na MD", "markdown z Excela", "wyciągnij tekst z PDF", albo daje plik Office/PDF do analizy. Microsoft MarkItDown (pip)…
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.
meta-multi-format-export-pack
From one piece of source content, render four deliverables: .docx report, .pptx slides, .xlsx data, and an HTML/PDF public version.