agentmods.dev

lembretes

lembretes is a skill for Claude Code from DGatoM/DG-Claw. It costs 0 tokens per session (1,780 once invoked), scanned B, original, MIT.

A reminder system that displays alerts, sends phone notifications when enabled, and repeats them until the person confirms or postpones the reminder.

In plain words
What is it for?
Use it for reminders such as calling someone, taking something out of the oven, or doing a task at a specified time.
Why use it?
It helps prevent important tasks from being forgotten after a single notification.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

not rated 20repo +5 2d ago B scan 0 tokens original MIT

Good fit Use it for reminders such as calling someone, taking something out of the oven, or doing a task at a specified time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dgatom/dg-claw/lembretes
View source ↗ DGatoM/DG-Claw
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.

Any agent
npx skills add DGatoM/DG-Claw --skill lembretes
Clone the repo
git clone --depth 1 https://github.com/DGatoM/DG-Claw

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.

agentmods badge for lembretes

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgatom/dg-claw/lembretes/github.svg)](https://agentmods.dev/skills/dgatom/dg-claw/lembretes)
Your own site
<a href="https://agentmods.dev/skills/dgatom/dg-claw/lembretes"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/lembretes/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 lembretes

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgatom/dg-claw/lembretes"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/lembretes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,780 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.01780
Opus 5.5 $0.00000 $0.00712
Sonnet 5.5 $0.00000 $0.00356
Haiku 4.5 $0.00000 $0.00178

Measured 19d ago against content hash 2a972b2d342f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

lembretes scanned grade B 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 19d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| 3 | a caixa não está disponível | peça ao dono para rodar `sudo dgclaw agente reparar <seu-slug>` |
skills/lembretes/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dgclaw:lembretes, avisar o dono e insistir até ele confirmar

O dono pede "me lembra de ligar pro contador amanhã às 9h". Você agenda pela API do DG Claw Web. Na hora, o próprio DG Claw avisa de três jeitos ao mesmo tempo: uma faixa ⏰ no alto da conversa, um aviso no celular (se ele ativou) e um recado para você. E repete a cada 5 minutos, até 12 vezes, até ele confirmar. Quem insiste é o DG Claw, não você.

Lembrete ou rotina?

  • Lembrete (esta skill): avisar o dono de alguma coisa e esperar a confirmação dele.
  • Rotina (skill agenda): você fazer um trabalho num horário (mandar o resumo, conferir algo). Se a rotina precisar da confirmação do dono, ela mesma cria um lembrete.

Como criar

Use o dgclaw-api (a documentação completa está em dgclaw-api GET /api/v1/lembretes/docs.md).

Prazo relativo ("daqui a 20 minutos", "em meia hora"): sempre daqui_min. O DG Claw faz a conta da hora no fuso certo. Não calcule hora na mão.

dgclaw-api POST /api/v1/lembretes '{"texto":"tirar o bolo do forno","daqui_min":20}'

Data e hora marcadas: rode date antes, para saber que dia é hoje e que dia da semana, e só então escreva a data completa. O fuso é o do servidor; mande a hora que o dono falou.

# uma vez
dgclaw-api POST /api/v1/lembretes '{"texto":"ligar pro contador","regra":{"tipo":"unico","data":"2026-10-20","hora":"14:30"}}'
# todo dia, até o fim do ano, insistindo de 10 em 10 minutos
dgclaw-api POST /api/v1/lembretes '{"texto":"tomar o remédio","fim":"2026-12-31","intervalo_min":10,"regra":{"tipo":"diario","hora":"08:00"}}'
# segunda e quarta
dgclaw-api POST /api/v1/lembretes '{"texto":"treino","regra":{"tipo":"semanal","dias":["seg","qua"],"hora":"18:00"}}'
# a cada 3 dias
dgclaw-api POST /api/v1/lembretes '{"texto":"regar as plantas","regra":{"tipo":"a_cada_n_dias","n":3,"inicio":"2026-10-17","hora":"20:00"}}'
  • Os tipos de regra são unico, diario, semanal e a_cada_n_dias. hora, dias, data e companhia vão dentro de regra.
  • Opcionais: intervalo_min (1 a 120, padrão 5), teto_envios (1 a 60, padrão 12), pelo_agente, titulo, fim. O campo agente você não precisa mandar: é sempre você.
  • Confirme ao dono com a regra_texto e a proxima que a resposta devolveu, nas palavras dele: "Combinado, toda segunda e quarta às 18:00. A próxima é segunda, 19/10 às 18:00." Se a resposta não bater com o que ele pediu, corrija na hora (PATCH) em vez de deixar passar.
  • Erro 400 traz erros com o motivo de cada campo: leia, corrija e tente de novo. Não invente outro campo.

Read the full file on GitHub · 98 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. 19d ago First seen · 98 lines · 0 tokens per session scan B 2a972b2d342f

Subscribe to this mod's changes

lembretes is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,780 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

Productivity
Related

lembretes compared with skills from other repositories

lembretes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lembretesDGatoM/DG-ClawSkill202d agoMITB0Claude Code
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
agentmailpaperclipai/paperclipSkill111kyesterdayMITA30Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
rowboat-spacesrowboatlabs/rowboatSkill18kyesterdayApache-2.0A60Claude Code, Codex
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex
pinchtab-mcppinchtab/pinchtabSkill11k10d agoMITA52Claude Code, Codex