agentleFS
ohanyanohanyan/adulting/skills/morning-reset/SKILL.md

morning-reset

Skill1 starsChanged 7 months agoMITView on GitHub

Stoic morning launcher. Premeditatio malorum, one intention, the day's hard thing, and a virtue to rehearse. Use at the start of the day before email and Slack.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this before email, before news, before anything reactive.

    line 8
  2. Distinctive:

    Ask the user, and capture their one-line answer to each:

    line 19
  3. Distinctive:

    Write it down. One sentence.

    line 29
  4. Distinctive:

    If yes, commit. If no, negotiate a specific earlier-than-usual time.

    line 35
  5. Very specific:

    Write a short morning page to ~/adulting-data/journal/YYYY-MM-DD-morning.md:

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/morning-reset

Run this before email, before news, before anything reactive.

Step 1: Marcus Aurelius reminder (30 seconds)

Print this aloud, or read it slowly:

"Today I will meet the meddler, the ungrateful, the arrogant, the deceitful, the envious, the unsociable. All of them are these things because they have not learned the difference between good and evil. But I, who have studied the nature of the good and seen it is beautiful, and the nature of the bad and seen it is ugly, cannot be harmed by any of them." — Marcus Aurelius, Meditations 2.1

Step 2: Premeditatio malorum (2 minutes)

Ask the user, and capture their one-line answer to each:

  1. What could go wrong today? Name the most likely three obstacles. Person, event, or internal (fatigue, frustration, a craving).
  2. How would a person of virtue respond? One sentence per obstacle.
  3. Which cardinal virtue will today demand most? Courage, discipline, justice, or wisdom? Pick one.

Step 3: The one thing (1 minute)

"What is the single outcome that, if accomplished, would make today a win, even if nothing else goes right?"

Write it down. One sentence. Not a todo list. The week-making task from the weekly review may be the answer.

Step 4: The day's hard thing (McRaven / Goggins)

"What is the first uncomfortable task on the list, and will you do it before 9am?"

If yes, commit. If no, negotiate a specific earlier-than-usual time.

Step 5: The people (Love Map + Bids)

"Who in your house is carrying something today that you should know about?" "What is one bid for connection you will turn toward, not away from, today?"

A bid is any small attempt at attention, affection, or connection. A toddler pointing at a bug. A partner mentioning a colleague. A friend texting a link. Turning toward is the marriage.

Step 6: Output

Write a short morning page to ~/adulting-data/journal/YYYY-MM-DD-morning.md:

# Morning page — <date>

## Premeditatio
- Obstacle 1: <x> → virtue response: <y>
- Obstacle 2: <x> → virtue response: <y>
- Obstacle 3: <x> → virtue response: <y>

## Virtue to rehearse
<courage | discipline | justice | wisdom> — because <why today>.

## The one thing
<sentence>

## The hard thing, before 9am
<sentence>

## People I will notice
- <name>: <what they are carrying>
- One bid I will turn toward: <what>

Print it back to the user. Then stop. Do not give advice or commentary unless asked.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.