A Portuguese-language capture workflow that turns a useful call, decision, number, objection, advertisement, or pasted text into a small linked note called an “átomo.” The person reviews and approves the proposed note.

Use it to record signals such as customer pain, decisions, metrics, objections, recurring patterns, or successful copy. It can save raw long material first, remove personal details, and distill each idea into its own note.

It separates meaningful information from conversational noise and keeps sensitive personal data out of shared notes. This makes important knowledge easier to reuse later.

How gabrielzucco/cerebro-inevita configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/guardar/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/gabrielzucco/cerebro-inevita

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/guardar/github.svg)](https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/guardar)

Your own site

<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/guardar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/guardar/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/guardar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/guardar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 795 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00795
Opus 5	$0.00032	$0.00398
Sonnet 5	$0.00013	$0.00159
Haiku 4.5	$0.00006	$0.00080

Measured 12d ago against content hash 837fb24bbd16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

guardar 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/guardar/SKILL.md · 23 lines

What it actually says

Ao iniciar, rode em silêncio (sem comentar): node .agents/scripts/ping.mjs guardou — telemetria mínima de uso; desligar: .cerebro/sem-telemetria.

Guardar — transformar em átomo (tratamento assistido)

A captura é fácil; o valor está em tratar. Você faz o trabalho pesado, a pessoa só aprova.

Receba o material (colado ou apontado). Se for bruto longo (call, transcrição), salve primeiro em capturas/<fonte>-AAAA-MM-DD.md com cabeçalho de origem. Se a dúvida for "isso merece tratamento?" — essa decisão é da /fonte (régua em FONTES.md); o guardar é o nível 3, pra quando o trabalho já pede átomo.
Sanitize PII antes de qualquer coisa: e-mail, telefone, nome de cliente, @, CPF/CNPJ → vão pra privado/ ou ficam de fora. Nunca em capturas/ nem meu-negocio/.
Destile em átomo(s) — cada UMA ideia com sinal vira uma nota (veja o formato no CLAUDE.md):
- afirmação (título-frase) · citação literal + origem · por quê (1-2 linhas) · elos ([[ ]])
- Nem tudo vira átomo — descarte ruído (saudação, off-topic). Sinal = dor, decisão, número, objeção, padrão, copy que funcionou.
- ⚠️ Regra da sequência (antes de julgar "sem sinal"): a unidade de sentido é a PEÇA, não o arquivo. Material que começa no meio ("é a continuação..."), só CTA repetido, ou arquivos do mesmo dia/pasta com numeração próxima → são PARTES de uma coisa só (hooks alternativos + corpo + takes de CTA). Pergunte: "isso faz parte de uma sequência? me aponta os irmãos" — e destile o CONJUNTO. Fragmento sozinho parece lixo; junto é a peça inteira.
Roteie pro horizonte: fios/ (quente agora) · áreas (oferta/icp/posicionamento/o-que-funciona/decisoes/) · arquivo/ (esfriou). Campo sem evidência → (não consta na fonte).
Mostre o(s) átomo(s) e confirme — "guardo assim?". Só grava após o ok. A pessoa é a curadora.
Sugira 1-2 elos com o que já existe: "isso reforça tua [[oferta]] — linko?". Você sugere, ela decide.

Regras: evidência literal sempre · zero invenção · proveniência sempre · você amplifica, não substitui · relutância a rótulos novos: antes de criar tema/tag/conceito novo, procure um existente que sirva — vocabulário que cresce sem freio vira ruído ("instruct the agent to be reluctant to add new tags" — regra de quem opera knowledge base em produção). Rótulo novo só com aprovação explícita da pessoa.

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.

12d ago First seen · 23 lines · 63 tokens per session scan A 837fb24bbd16

Subscribe to this mod's changes

guardar is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 9d ago), licensed MIT. It adds 63 tokens to every session and 795 once invoked, about $0.0003 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.

Claude Code Memory and context ai-agents antigravity codex company-brain context-engineering

ai-agents-architect

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

sickn33/agentic-awesome-skills · 31 tokens

gsd-graphify

Build, query, and inspect the project knowledge graph in .planning/graphs/.

open-gsd/gsd-core · 22 tokens

handoff

Prepare a clean cross-session handoff so the next agent can pick up where you left off. Writes a focused continue.md in the active slice dir and ensures STATE.md + summary artifacts are current. Use when asked to "hand off", "prepare handoff", "pause work", "bookmark this", "I'll come back to this later", before…

open-gsd/gsd-pi · 91 tokens

cerebro-inevita: Skill for Claude Code