Cron

What it does

When your agent uses it

• Tasks that involve Scheduled and recurring tasks

Example prompts

• “schedule”
• “reminder”
• “/cron”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Никогда не эмулируй расписание через sleep, циклы в Bash или
2. 2Разовое («напомни…») — всегда --at + --delete-after-run.
3. 3at пиши со смещением зоны ПОЛЬЗОВАТЕЛЯ (, напр. +05:00`);
4. 4Prompt задания — самодостаточный: исполняет отдельная сессия без
5. 5Мониторинговым заданиям («проверь и скажи, если что-то новое») вели в
6. 6Recursion guard: если текущий запрос сам помечен [CRON JOB ...] —
7. 7После add/remove подтверди пользователю результат строкой из list

What it can do on your machine

Read from SKILL.md and the folder at commit 7828ed6. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cron loads about 856 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~54

When it runs · the whole SKILL.md, loaded when a task matches

~856

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from smixs/agent-second-brain at commit 7828ed6, republished under its MIT licence (© smixs). 283 words, ~856 tokens.

name

cron

description

Управление собственным расписанием — напоминания, рутины, периодические задачи. Триггеры — "напомни", "каждый день/час/утро", "по расписанию", "schedule", "reminder", "отмени напоминание", "что запланировано".

# Повторяющееся по cron-выражению (время местное — указывай --tz)
uv run --project .. python -m d_brain.cron add \
  --prompt "Собери утреннюю сводку: вчерашний daily, goals недели" \
  --cron "0 9 * * *" --tz "${TZ:-UTC}" --id morning-brief

# Интервал в секундах
uv run --project .. python -m d_brain.cron add \
  --prompt "Проверь inbox в vault, новое разложи по карточкам. Если пусто — начни ответ с [SILENT]" \
  --every 3600

# Разовое напоминание: ВСЕГДА --at + --delete-after-run
uv run --project .. python -m d_brain.cron add \
  --prompt "Напомни про звонок с подрядчиком" \
  --at "2026-06-12T18:00:00<offset>" --delete-after-run   # <offset>, напр. +05:00

uv run --project .. python -m d_brain.cron list
uv run --project .. python -m d_brain.cron remove <id>
uv run --project .. python -m d_brain.cron enable <id>   # вернуть авто-отключённый

© smixs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in vault/.claude/skills/cron of smixs/agent-second-brain.

Open the folder on GitHubat commit 7828ed6