transcrever

transcrever is a skill for Claude Code from emidio-trancoso/advocacia-aberta. It costs 79 tokens per session (2,527 once invoked), scanned A, original, MIT.

A local tool that turns audio or video recordings into timestamped Portuguese text and subtitle files.

In plain words
What is it for?
Use it to transcribe meetings, hearings, interviews, calls, and consultations into Markdown and SRT files, with optional speaker labels and key excerpts.
Why use it?
It makes recordings searchable and reviewable while keeping the media on the user's computer for privacy.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: installed under .agents/ (shared by several agents).

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the advocacia-aberta plugin — 10 skills shipped together

Good fit Use it to transcribe meetings, hearings, interviews, calls, and consultations into Markdown and SRT files, with optional speaker labels and key excerpts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add emidio-trancoso/advocacia-aberta
Claude Code
/plugin install advocacia-aberta

Made for: Claude Code.

Or install advocacia-aberta, the plugin that ships this one along with the rest of its 10 skills.

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 transcrever

README.md
[![agentmods](https://agentmods.dev/badge/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever/github.svg)](https://agentmods.dev/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever)
Your own site
<a href="https://agentmods.dev/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever"><img src="https://agentmods.dev/badge/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever/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 transcrever

Your own site · 80×15
<a href="https://agentmods.dev/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever"><img src="https://agentmods.dev/badge/skills/emidio-trancoso/advocacia-aberta/1.2-transcrever.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,527 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 $0.00079 $0.02527
Opus 5 $0.00039 $0.01264
Sonnet 5 $0.00016 $0.00505
Haiku 4.5 $0.00008 $0.00253

Measured 12d ago against content hash f74a5a37e662, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

transcrever 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 12d 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.

.agents/skills/1.2-transcrever/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transcrever — Áudio e Vídeo em Texto

Esta skill transforma uma gravação em texto. Serve para qualquer gravação: reunião com cliente, audiência, depoimento, sustentação oral, áudio de WhatsApp, gravação de consulta ou ligação. O resultado é uma legenda (.srt) e uma transcrição (.md) limpa, com a hora de cada fala entre colchetes ([HH:MM:SS]) e um marcador [?] no lugar do nome de quem fala.

A transcrição roda 100% no seu computador (offline). Nenhum áudio sai da sua máquina — bom para sigilo profissional.

Aviso honesto de tempo: transcrever 1 hora de áudio leva cerca de 15 a 25 minutos de processamento. É normal. O computador fica trabalhando esse tempo.

Ao final, há um passo opcional que identifica quem é cada pessoa nas falas e separa os trechos mais importantes — útil quando você tem o contexto da gravação (uma ata, uma pauta, uma lista de presentes, ou simplesmente sabe quem participou).

Instrução

Considere <arquivo-de-midia> o caminho relativo do áudio ou vídeo informado pelo usuário. Exemplos:

  • casos/Silva-vs-Maria/autos/audiencia.webm
  • casos/reuniao-cliente-joao/reuniao.m4a
  • casos/Silva-vs-Maria/autos/audio-whatsapp.ogg

Se o caminho não tiver sido informado, detecte o arquivo aberto no editor quando essa informação estiver disponível; caso contrário, pergunte ao usuário.

Os caminhos abaixo são todos relativos à raiz do projeto aberta no agente. Substitua <arquivo-de-midia> pelo caminho real, sempre entre aspas.


Passo 1 — Verificar o ambiente

Antes de transcrever, confira se as ferramentas necessárias e o modelo de reconhecimento de voz estão instalados:

which whisper-cli ffmpeg
ls ~/.whisper-models/ggml-medium-q5_0.bin 2>/dev/null

Se qualquer uma dessas linhas não encontrar o que procura (saída vazia ou mensagem de "não encontrado"), o ambiente ainda não está pronto. Nesse caso, oriente o usuário a executar a skill preparar-ambiente, que instala tudo automaticamente (as ferramentas e o modelo de voz). Não tente instalar nada aqui; apenas aponte para essa skill e pare.

Read the full file on GitHub · 226 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. 12d ago First seen · 226 lines · 79 tokens per session scan A f74a5a37e662

Subscribe to this mod's changes

transcrever is a skill published in the GitHub repository emidio-trancoso/advocacia-aberta (49 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 2,527 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

advogado-criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

sickn33/agentic-awesome-skills · 42 tokens

advogado-especialista

Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.

sickn33/agentic-awesome-skills · 38 tokens

advogado-criminal-v2

ADVOGADO CRIMINALISTA SENIOR — ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should…

diegosouzapw/awesome-omni-skills · 98 tokens

redator-adversarial

Redação e revisão adversarial de peças processuais. Use quando precisar redigir peça (inicial, contestação, réplica, recurso) com estrutura padrão, ou testar peça pronta simulando o juiz (admissibilidade, clareza, requisitos formais) e a parte contrária (contra-argumentos, flancos), gerando relatório de fragilidades…

neimaciel/redator-adversarial · 87 tokens

prazo-sentinel

Cálculo e alerta de prazos processuais. Use quando precisar contar prazo de intimação (dias úteis CPC, corridos CLT/CPP), verificar dobra de prazo (Fazenda, Defensoria, litisconsortes), aplicar suspensão de fim de ano, montar a agenda semanal de prazos da carteira, ou reagir a prazo perdido (justa causa). Adapta tom…

neimaciel/prazo-sentinel · 99 tokens

societario-pro

Direito societário consultivo e contencioso. Use para constituição de sociedade (LTDA x S.A. x SLU, contrato social com cláusulas de impasse e saída), acordo de sócios (vesting com cliff, tag along, drag along, não-concorrência, deadlock buy-or-sell, opção de compra), alterações societárias (cessão de quotas…

neimaciel/societario-pro · 126 tokens