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 joaoguirunas/team-os --skill doc-to-markdowngit clone --depth 1 https://github.com/joaoguirunas/team-osWrote 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/joaoguirunas/team-os/doc-to-markdown)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/doc-to-markdown"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/doc-to-markdown/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/joaoguirunas/team-os/doc-to-markdown"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/doc-to-markdown.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 | $0.00091 | $0.02176 |
| Opus 5.5 | $0.00036 | $0.00870 |
| Sonnet 5.5 | $0.00018 | $0.00435 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
doc-to-markdown 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documento → Markdown (local)
Agente não lê binário bem e paga caro por isso. Esta skill transforma o documento em um .md na mesma máquina, com tabelas preservadas e cabeçalho de origem, e o agente passa a trabalhar com o caminho do .md — nunca com o conteúdo colado no prompt.
Regra zero — o documento não sai da máquina
Contrato, extrato, nota fiscal, holerite, documento com CPF/CNPJ: nenhuma conversão usa serviço externo.
- PROIBIDO
--ocr hosted, API de "parse" na nuvem, upload para conversor online, MCP que envie o arquivo. - PROIBIDO baixar ferramenta nova sem o usuário pedir. Use o que já está instalado (
command -v). - Se nenhuma ferramenta local resolve: pare e peça ao usuário (exportar CSV, instalar a ferramenta, mandar versão com texto). Pendência declarada vale mais que conversão vazada.
Ordem de ferramentas
Verifique antes: command -v pandoc pdftotext pdfinfo xlsx2csv ocrmypdf tesseract.
| Entrada | 1ª escolha | Alternativa | Se nada servir |
|---|---|---|---|
| PDF pequeno (≤ ~10 páginas, só para ler) | Read nativo do Claude Code | pdftotext -layout |
— |
| PDF de texto (maior, ou para guardar) | pdftotext -layout (poppler) |
Read nativo em faixas de páginas | pedir brew install poppler |
| PDF escaneado (sem camada de texto) | ocrmypdf / tesseract locais, se instalados |
— | [DOC PENDENTE — precisa de OCR local] |
| DOCX, ODT, RTF, HTML, EPUB | pandoc -t gfm |
— | pedir ao usuário salvar como PDF de texto |
| PPTX | pandoc -f pptx (pandoc recente) |
Read nativo do PDF exportado | pedir export em PDF |
| XLSX | pandoc -f xlsx só se pandoc --list-input-formats listar xlsx |
xlsx2csv, ou python3 com openpyxl se já instalado |
pedir ao usuário exportar CSV |
| CSV / TSV | pandoc -f csv (vira tabela) |
ler direto | — |
@firecrawl/anydoc (opcional) |
ver seção própria | — | — |
Observações:
python3puro (stdlib) não lê xlsx de forma confiável — não improvise parser de XML.- pandoc antigo não lê
xlsxnempptx; confira a lista de formatos antes de prometer. .doc,.xlse.ppt(formatos binários antigos): peça ao usuário salvar como.docx/.xlsx/.pdf.
What ships with it
1 file 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.
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.
- 2d ago First seen · 134 lines · 91 tokens per session scan A 66a067fefc5c
doc-to-markdown is a skill published in the GitHub repository joaoguirunas/team-os (5 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 2,176 once invoked, about $0.0004 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 2026-10-22.
Other skills, from other repositories
literature-matrix-builder
A tool for turning a collection of research papers in PDF format into an organised literature library and comparison spreadsheet. It can find identifiers such as DOIs, retrieve publication details, check for retractions, and prepare reference lists.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
historical-data-manager
Extract, clean, and organize legacy construction data from archives. Migrate historical project data, cost records, and schedules into modern formats.
pdf-report-generator
Automatically generate PDF reports from construction data. Create formatted project reports with charts and tables.
cwicr-report-generator
Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.