A Portuguese-language daily planning skill that reads priorities, open tasks, calendar events, and the previous day’s notes. It proposes three tasks for the day and records the approved choices in a weekly diary.

Use it when starting the workday to review commitments, suggest the day’s three priorities, and save the confirmed plan.

It gathers scattered planning information into one agenda while leaving the final choices to the person.

abrir-dia — Skill for Claude Code by pe-menezes

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 pe-menezes/pm-chief-of-staff --skill abrir-dia

Clone the repo

git clone --depth 1 https://github.com/pe-menezes/pm-chief-of-staff

Made for: Claude Code.

Or install pm-chief-of-staff, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

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/pe-menezes/pm-chief-of-staff/abrir-dia/github.svg)](https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/abrir-dia)

Your own site

<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/abrir-dia"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/abrir-dia/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/pe-menezes/pm-chief-of-staff/abrir-dia"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/abrir-dia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 990 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	$0.00100	$0.00990
Opus 5	$0.00050	$0.00495
Sonnet 5	$0.00020	$0.00198
Haiku 4.5	$0.00010	$0.00099

Measured 12d ago against content hash 3d4f47dfc7be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

abrir-dia 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.

seeds/abrir-dia/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Abrir o dia

Semente do pm-chief-of-staff. Este arquivo é SEU: peça pro agente mudar qualquer passo ("quero que a abertura sempre inclua X") e ele edita esta skill na hora.

Escrita: siga o cânone do CLAUDE.md desta pasta. Na ausência dele: sem travessão (use vírgula, parênteses ou dois pontos), frases curtas e densas, 1 linha por item.

Monta o dia em cima do que já está escrito: prioridades, tasks abertas, agenda, e a semente que o fechamento de ontem deixou. Propõe as 3 do dia; a pessoa valida antes de cravar.

Princípios

As prioridades de CRITICAL_FACTS.md filtram tudo: task que não ancora em prioridade precisa de motivo pra entrar no dia.
As 3 do dia vivem no diário da semana, bloco ## 3 do dia , DD/MM no topo.
A skill propõe, a pessoa valida antes de cravar. Nunca decidir pela pessoa.

Fluxo

Ler o estado: CRITICAL_FACTS.md (prioridades) · o diário da semana corrente · a linha **→ amanhã:** do fechamento de ontem (candidata mais forte a #1 do dia) · o log memory/ mais recente.
Agenda: se existir .claude/skills/_shared/capacidades.md, ler a linha agenda do dia e puxar os eventos de hoje pelo que está em como chamar, com provider identificando a fonte. Sem o módulo, com essa linha vazia ou pela metade (só uma das duas colunas), ou se a busca falhar (conector expirado, máquina sem ele), perguntar em 1 linha: "como tá tua agenda hoje? (reuniões e janelas livres)". A abertura do dia não para por causa da agenda.
Varrer o backlog: grep -- "- \[ \]" no diario/ inteiro, sem âncora de início de linha (subtask indentada conta). Categorizar: hoje (prazo hoje ou resolve em reunião de hoje) · atrasadas · esta semana · espera (bloqueada por terceiro). Task atrasada de outro tema se lê junto com as novas: se uma nova invalida a velha, propor fechamento da velha, não re-execução.
Propor as 3 do dia, cada uma ancorada explícita ("{tarefa} (ancora prioridade 1)"). Regras:
- A semente **→ amanhã:** de ontem é a candidata mais forte a #1.
- Reunião não é "3 do dia" (acontece de qualquer jeito); as 3 são execução.
- Calibrar contra a agenda: contar as horas realmente livres. Sobrando menos de 2h, propor 1 movimento + 1 monitor no máximo, e dizer isso na abertura. Três ambiciosas num dia sem janela garantem o fracasso por calibragem, não por execução.
Gravar no topo do diário da semana: ## 3 do dia , DD/MM + as 3 numeradas e ancoradas. Mesmo dia roda de novo: sobrescreve o bloco. Dia novo: cria e deixa o anterior no histórico.
Responder curto: agenda em 1 bloco · as 3 propostas · 1 a 2 perguntas críticas se houver contradição detectada. Aguardar validação antes de cravar.

Read the full file on GitHub · 39 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.

12d ago First seen · 39 lines · 100 tokens per session scan A 3d4f47dfc7be

Subscribe to this mod's changes

abrir-dia is a skill published in the GitHub repository pe-menezes/pm-chief-of-staff (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 990 once invoked, about $0.0005 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 Planning Productivity chief-of-staff claude-code-plugin product-management second-brain

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

agenticnotetaking/arscontexta · 50 tokens

abrir-dia

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

Abrir o dia

Princípios

Fluxo

What this file has done since we first saw it

Other skills, from other repositories

next

create-slide-deck

pm-setup

opportunity-assessment

competitive-intel

experiment-review