mc-manage-automations

name

mc-manage-automations

description

Schedule, list, edit, or remove a recurring agent task (cron / interval) in `config/scheduler/tasks.json`. Use for cross-collection digests, notifications, or any standalone recurring prompt ("毎朝7時に天気", "every weekday 8am check email", "schedule a weekly cleanup"), or to list/stop automations. EXCEPTION — do NOT create a task here to keep ONE collection's records fresh (e.g. "update the stock-quotes daily", "refresh these quotes every morning", "re-poll these URLs"): instead add an `ingest` block with `kind: "agent"` to THAT collection's own `schema.json` (it self-refreshes on schedule and from its Refresh button; syntax in `config/helps/collection-skills.md` → "Scheduled agent refresh"). Read this skill body in full before writing `tasks.json` — the entry format is structured, not free-form.

Automations manager

A bundled MulmoClaude preset skill (mc- prefix = launcher-managed; do not edit this file in the workspace, it is overwritten on every server boot).

Help the user schedule recurring agent tasks — the things that wake the agent up on a cron / interval to run a fixed prompt. State lives in a single JSON array at config/scheduler/tasks.json (cwd-relative; the agent runs with cwd set to the workspace root, so every path in this file is plain cwd-relative); the auto-refresh hook re-registers tasks after every Write/Edit so changes take effect immediately.

End with a one-line confirmation ("Scheduled weather-morning, daily 07:00 UTC." / "Stopped weekly-cleanup.") so the user can verify without scrolling.

First: is this just refreshing ONE collection?

Before writing a tasks.json automation, check what the recurring work actually is. If it's "keep one collection's records up to date" — refresh stock quotes, re-poll a set of watched URLs, pull fresh figures for every row — do NOT create an automation here. Add an ingest block to that collection's own schema.json instead:

"ingest": {
  "kind": "agent",
  "schedule": "daily",
  "atHour": 21,
  "role": "<a role that owns the tools the refresh needs>",
  "template": "templates/refresh.md"
}

and write templates/refresh.md telling the worker how to refresh the records. The full contract is in config/helps/collection-skills.md → "Scheduled agent refresh". On schedule (and on the collection's Refresh button) the host runs a hidden background worker that edits the records.

Prefer this over a tasks.json automation whenever the work is one collection's refresh: the schedule lives with the collection — it travels when the skill is copied and is deleted when the collection is, instead of leaving an orphan task here whose prompt points at records that may no longer exist. (Editing data/stock-quotes/items/*.json daily? That's ingest.kind: "agent" on the stock-quotes schema, not an automation.)

Use the tasks.json automation below only for work that isn't one collection's refresh: cross-collection digests, notifications, or an arbitrary recurring prompt.

Workflow 1: schedule a new automation

Triggers: "毎朝 7 時に天気を", "every weekday 8am check email", "schedule a weekly cleanup", "1時間ごとに news 確認".

Step 1 — convert local time to UTC. Schedules are stored / compared in UTC (the task-manager calls Date.getUTCHours/Minutes). When the user gives a local time, convert before writing. E.g. "07:00 JST" → "16:00" of the previous UTC day? No — 07:00 JST is 22:00 UTC of the previous day. JST is UTC+9, so 07:00 JST = 22:00 UTC (yesterday). (Run the math, don't trust your reflex — UTC offsets are a classic typo source.)

Step 2 — pick a kebab-case id. Memorable, lowercase, hyphen-separated: weather-morning, weekly-cleanup, hourly-news.

Step 3 — Read the existing file (or create the array if missing):

config/scheduler/tasks.json

It's a single JSON array. Append a new entry:

{
  "id": "weather-morning",
  "name": "Morning weather",
  "description": "Check today's weather every weekday at 7am.",
  "schedule": { "type": "daily", "time": "22:00" },
  "missedRunPolicy": "runOnceImmediately",
  "enabled": true,
  "roleId": "general",
  "prompt": "What's the weather today?",
  "createdAt": "2026-05-11T08:00:00.000Z",
  "updatedAt": "2026-05-11T08:00:00.000Z"
}

Schedule kinds:

• { "type": "daily", "time": "HH:MM" } — daily at the given UTC time.
• { "type": "interval", "intervalMs": <ms> } — every N ms. 60000 = 1 min, 3600000 = 1 hour, 86400000 = 1 day.

missedRunPolicy:

• runOnceImmediately — if the scheduled time was missed (laptop asleep, server down), run once on next wake. Use for status checks ("what's the weather", "any new emails").
• skip — drop missed runs. Use for news polls (no point catching up).

Cadence suggestions (offer these by default unless the user asks for something specific):

• News polling → hourly interval
• Digest reports → daily at a fixed local time
• Cleanup tasks → weekly (use interval of 604800000 ms)
• Calendar / inbox sync → every 4 hours (14400000 ms)

The auto-refresh hook fires on Write/Edit and re-registers tasks, so the new automation activates immediately.

Workflow 2: list / browse

Triggers: "show my automations", "登録 task 全部", "何が走ってる?".

Read config/scheduler/tasks.json and present name + schedule + enabled for each. Convert the stored UTC time back to the user's local zone when displaying ("daily 07:00 JST" reads better than "daily 22:00 UTC").

If filtered ("enabled だけ", "daily のだけ"), filter before showing.

Workflow 3: update

Triggers: "weather-morning を 8 時に変更", "disable foo-task", "change the prompt for bar".

Read the current array, find the entry by id, modify the relevant fields, bump updatedAt to the current ISO timestamp, write back. Preserve every other field unless the user explicitly asked to change it.

To pause a task without deleting, set enabled: false.

Workflow 4: remove

Triggers: "stop the foo task", "weekly-cleanup 削除".

Only when the user explicitly asks. Read the array, splice the entry by id, write back. Confirm afterward.

If the user is unsure, suggest enabled: false as a reversible alternative.

Tone

Friendly, practical. When suggesting a cadence, lead with what makes sense ("morning weather → daily at your local 7am") rather than asking the user to pick from daily / interval / hourly cold. If the user phrases a time naturally ("毎朝"), convert to a concrete UTC value rather than asking back.