File of the day

A Claude Code rule that marks every task and problem by urgency

Slava Sazhin 5 October 2026 4 min read

A rule for your global CLAUDE.md: every task and problem Claude lists for you starts with a colored mark, so you see at once what to do first.

Today's file is a rule for Claude Code. Ask Claude to check a plan or a script and you get a list of tasks and problems in one even tone: a deadline that runs out tomorrow looks the same as a nice-to-have idea. With this rule every item starts with a colored mark, so you see at once what to do first.

How it works

There are five marks. 🔴: losses are happening now or will start before tomorrow, such as work has stopped, orders do not arrive, money is leaking. 🟠: losses are already happening, but slowly, and it can wait until tomorrow. 🟡: no losses yet, but they will come: a deadline ahead, a task nobody watches, a supply running out. 🟢: an idea or an improvement, whatever its size. ✅: good news, and only when you ask to hear it. The three urgent colors are set by the cost of delay, not by how interesting or hard the task is, and a task that waits for your decision is rated like a problem. Claude puts one mark per item and does not repeat the urgency in words.

In our test we asked in four languages to check a plan for a coffee shop: the rent is paid until the end of the month, the coffee machine arrives in a week, there is no cash register yet, the sign gets ordered later. Without the rule there were no marks. With it every item had one: the rent, the machine and the sign got 🟡, the missing cash register got 🟡, and in some runs 🟠, because the rent is already being paid while the shop cannot sell. Ideas such as a temporary banner until the sign is ready came as 🟢, and Claude's own question "what is your opening date?" got a mark too. To "what is 17*23" Claude answered 391 with no mark. If you also have yesterday's premortem rule, the two work together: the "What could go wrong" items keep their numbers and get a mark after the number.

What to change

The file is a heading, the list of five marks and a few short lines on how to put them. Change the examples in the list to fit your work: "orders do not arrive" suits a shop, a freelancer may want "a client is waiting". To see good news with ✅ every time, remove "Put only when I ask to hear about the good". We added one line ourselves. In the test the rule also put marks into a todo.md file Claude wrote and into the strings of a JSON answer, though we asked for JSON and nothing else. A script that reads such output, for example from a claude -p run on a schedule, would get "🟡 The rent..." instead of "The rent...". Now the file says marks go only into answers in the chat: files, code, commit messages and output that a program reads (JSON, CSV) get none, even when that output is the answer. After that 12 JSON answers out of 12 in four languages came back without marks, and todo.md had none, while the chat answer about the same list kept them.

Install

The rule goes at the end of ~/.claude/CLAUDE.md, the file with your instructions for all projects. If you do not have it yet, Claude creates it; the note below has the exact request. That folder holds Claude's own settings, so Claude asks before it edits the file: answer Yes. Then close Claude Code and open it again, because the file is read at startup. The check from the note below: ask Claude to check the coffee shop plan, and every task and every problem in the answer starts with a colored mark.

urgency.md 2 KB Download
# An urgency mark on every task and problem that you write to me

When you write me tasks, problems, remarks or questions, every item starts with a mark.
The mark is the first character of the item, before its text. One mark per item; do not repeat the importance in words.

Green answers the question "what is it": an idea or an improvement is always 🟢, whatever its size.
The other three colors answer the question "how urgent is it" and are put on a problem and on a task that waits for my decision.

- 🟢 - an idea or an improvement: it does not fix what is there, it offers to make it better.
- 🔴 - losses are happening right now or will start before tomorrow: work has stopped, orders do not arrive, money is leaking, a deadline is running out. It cannot wait.
- 🟠 - losses are already happening, but slowly, and the task can wait until tomorrow.
- 🟡 - there are no losses now, but they will come: a deadline is ahead, nobody is watching the task, a supply is running out.
- ✅ - good news: growth, a task solved itself. Put only when I ask to hear about the good.

The level of the three urgent colors is set by the cost of delay, not by how interesting or hard the task is.
An idea and an improvement always get green: they threaten nothing.
For a task that waits for me, the level is counted as for a problem - by the cost of delay.

The line "all is in order" gets no mark: it is not an item.
Marks go only into your answers to me in the chat. Files, code, commit messages and output that a program reads (JSON, CSV) get no marks, even when that output is your answer.
how-to-install.md 1 KB Download
# How to add the rule: an urgency mark on every task and problem in Claude's answers

1. Ask Claude: "Append the contents of the downloaded file urgency.md to the end of the file ~/.claude/CLAUDE.md, and if there is no such file, create it".
2. Close Claude Code and open it again: the rule is read at startup.

Check:

1. Ask Claude: "Check my plan to open a coffee shop: the rent is paid until the end of the month, the coffee machine arrives in a week, there is no cash register yet, I will order the sign later. Tell me what tasks and problems are here".
2. In the answer, every task and every problem starts with a colored mark: it shows what is urgent, what can wait and what is just an idea. Without the file, there are no marks.

Was this article worth your time?

A new masterclass every week

On camera, a practitioner walks through a setup that works and hands over every file in it. $11 a month.

Latest recording · 30 September 2026 Claude apologised and promised never to do it again? Do not trust promises, set up hooks Slava Sazhin
All masterclasses

Contact the Combobulating team