Borrowing it
Nothing to install: this file belongs to gabrielzucco/cerebro-inevita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/transcrever/SKILL.mdgit clone --depth 1 https://github.com/gabrielzucco/cerebro-inevitaWrote 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/gabrielzucco/cerebro-inevita/transcrever)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/transcrever"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/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.
<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/transcrever"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/transcrever.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 | $0.00100 | $0.01302 |
| Opus 5.5 | $0.00040 | $0.00521 |
| Sonnet 5.5 | $0.00020 | $0.00260 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
transcrever scanned grade A with 1 finding 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 20d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Precisa de `ffmpeg`, `curl` e uma chave da API (grátis em console.groq.com): How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ao iniciar, rode em silêncio (sem comentar):
node .agents/scripts/ping.mjs transcrever— telemetria mínima de uso; desligar:.cerebro/sem-telemetria.
Transcrever — de gravação a texto citável
O elo que faltava: FONTES.md manda "reunião → transcrição, e o minuto que sustenta cada
uma", e /call pede transcrição pronta. Esta skill é quem produz esse texto.
Uma gravação, duas saídas, dois consumidores. A API devolve as duas granularidades na mesma resposta, então nunca se transcreve duas vezes — o que importa porque transcrição refeita dá timestamp diferente, e aí o corte de vídeo não bate mais com o que foi destilado.
| Saída | O que é | Quem usa |
|---|---|---|
<nome>.md |
blocos [H:MM:SS] + frontmatter |
você e a IA leem → /guardar, /call |
<nome>.words.json |
timestamp de palavra | máquina → esteira de cortes 9:16 |
⚠️ Nunca leia o .words.json no contexto. Duas horas passam de 200 mil tokens e não
cabem em janela nenhuma. Ele existe pra script consumir. O que se lê é o .md.
Passo 1 — conferir o ambiente (só na primeira vez)
python3 .claude/skills/transcrever/transcrever.py --doctor
Precisa de ffmpeg, curl e uma chave da API (grátis em console.groq.com):
export GROQ_API_KEY=... ou grave em ~/.config/groq/key. O doctor diz o comando de
instalação do que faltar.
Passo 2 — perguntar o destino ANTES de rodar
Uma pergunta só, e ela decide onde o texto mora:
- É call/reunião de trabalho? → destino natural é
capturas/, e o passo seguinte é/call. - É aula, podcast, material de estudo? →
capturas/, passo seguinte/guardar. - É pra cortar vídeo? → deixe as duas saídas junto do vídeo, não em
capturas/: a esteira precisa do.words.jsonao lado do arquivo-fonte.
Se a pessoa não souber, transcreva em capturas/ — dá pra mover depois; refazer custa uma
chamada de API e quebra os timestamps já citados.
Passo 3 — rodar
python3 .claude/skills/transcrever/transcrever.py <arquivo-ou-pasta> [--saida DIR] [--idioma pt]
What ships with it
2 files 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.
- 20d ago First seen · 93 lines · 100 tokens per session scan A eefe89428825
transcrever is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (7 stars, last pushed 20d ago), licensed MIT. It adds 100 tokens to every session and 1,302 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
check-docs
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
deep-test
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.
handoff
Guides the Claude Code agent through completing a task, selecting a handoff tier, building a valid completion-card, and performing a clean task handoff.
x-harness-admission
Teach the x-harness admission workflow and completion-card discipline.