A weekly maintenance command for a file-based vault: it archives old handovers, checks the memory index, and lists items waiting in the inbox. Archiving means moving files rather than deleting them.

Use it to review and archive completed handovers, validate memory files and links, and decide where inbox items belong.

It keeps operational notes organised while preserving the timeline and avoiding accidental data loss. It also exposes broken index links and untriaged items.

vault_gc — Command for Claude Code by PedroHenrique0713/brain-template

Install

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.

Clone the repo

git clone --depth 1 https://github.com/PedroHenrique0713/brain-template

Made for: Claude Code.

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/commands/pedrohenrique0713/brain-template/vault_gc/github.svg)](https://agentmods.dev/commands/pedrohenrique0713/brain-template/vault_gc)

Your own site

<a href="https://agentmods.dev/commands/pedrohenrique0713/brain-template/vault_gc"><img src="https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/vault_gc/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/commands/pedrohenrique0713/brain-template/vault_gc"><img src="https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/vault_gc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 988 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	$0.00051	$0.00988
Opus 5.5	$0.00020	$0.00395
Sonnet 5.5	$0.00010	$0.00198
Haiku 4.5	$0.00005	$0.00099

Measured 22d ago against content hash bc445e410a58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vault_gc 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 22d 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.

vault/.claude/commands/vault_gc.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute na ordem. Cada passo é independente — sem nada a fazer, siga. No fim, apresente o relatório do Passo 5.

⚠️ Arquivar = mover de pasta, nunca condensar ou apagar. Handovers e logs de tarefa são a linha do tempo do trabalho.

TODAY = data de hoje
Status encerrados: concluida, cancelada (e os legados finalizada, finalizado, concluido, cancelado)
Uma tarefa são dois arquivos (estado e .log.md); andam sempre juntos

Passo 1 — Arquivar tarefas encerradas

Para cada 07 - HANDOVERS/Tarefas/*.md (sem os .log.md, sem descer em Arquivo/) com status encerrado: promova para Memória/ o conhecimento durável que ainda não está lá (protocolo do AGENTS.md) e mova os dois arquivos para Tarefas/Arquivo/.

Passo 1b — Tarefas paradas (decisão do usuário)

Rode python3 "03 - RESOURCES/Scripts/gerar-ativas.py" e leia 07 - HANDOVERS/ATIVAS.md. Tarefa com ⚠️ (viva, sem toque há mais de 21 dias) e pausada há mais de 60 dias vão para o relatório com uma sugestão curta (pausar, encerrar, ou "segue viva porque X"). Não mude status sozinho.

Passo 2 — Arquivar handovers antigos

Mova para 07 - HANDOVERS/Arquivo/ todo 07 - HANDOVERS/*.md com data no nome anterior a TODAY − 21 dias. O mais recente fica sempre. ATIVAS.md nunca sai.

Passo 3 — Validar a Memória

STAGING: cada linha de Memória/STAGING.md → durável vira fato (ou complementa um existente); efêmero ou já registrado sai. Zere a lista. Ambíguo vai pro relatório.
Digestão da semana: leia os handovers e logs de tarefa novos desde o último gc e (a) atualize os fatos que mudaram, com invalidação explícita; (b) liste contradições entre fato e handover mais novo; (c) capture no STAGING o durável que ninguém anotou.
Sincronia: todo Memória/*.md (exceto INDEX e STAGING) tem exatamente uma linha de gancho — no INDEX.md ou numa skill de ~/.claude/skills/. Nenhum nos dois, nenhum sem.
Teto do INDEX: linhas acima de 320 caracteres (awk '/^- \[/ {if (length > 320) print NR": "length}' "Memória/INDEX.md") viram gancho puro; causa e medição vão para o arquivo do fato.
Perecíveis: "no momento", "atualmente", "pendente", "aguardando", "por enquanto" nos fatos e no INDEX → move para a tarefa ou remove.
Datas relativas ("segunda", "semana que vem", "amanhã") → data absoluta, ou remove se já passou.
Fatos-dossiê: fato com mais de ~4 KB provavelmente é documentação; sugira migrar o corpo para a pasta do projeto (só listar).
review: vencido: confira se ainda vale.
Fusão de feedbacks que se sobrepõem: poucas regras fortes > muitas fracas.

Read the full file on GitHub · 52 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.

22d ago Changed · +4 lines · +51 tokens per session bc445e410a58
1mo ago First seen · 48 lines · 0 tokens per session scan A 24f346cd6e40

Subscribe to this mod's changes

vault_gc is a command published in the GitHub repository PedroHenrique0713/brain-template (1 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 988 once invoked, about $0.0002 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.

Claude Code Memory and context ai-memory gemini-cli knowledge-base markdown obsidian

vault_gc

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Passo 1 — Arquivar tarefas encerradas

Passo 1b — Tarefas paradas (decisão do usuário)

Passo 2 — Arquivar handovers antigos

Passo 3 — Validar a Memória

What this file has done since we first saw it

Other commands, from other repositories

wiki-query

wiki-req

wiki-ingest

wiki-record

wiki-retro

wiki-discover