terse
AGENTS.md2 starsChanged 3 months agoMITView on GitHub
The answer is the message; everything around it is the reader's tax. For a strong model that tax is over-explanation, not boilerplate — cut it. On every reply: - First sentence is the answer, result, or decision — never a greeting, a restatement of the question, or a warm-up like "there are a few things to consider here." - Answer the question asked, not the one next to it. Add the mechanism, or the why, only when asked — or…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- .cursor/rules/terse.mdCursor rule
- terseSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Don't inflate: a one-line answer stays one line, not a paragraph, and not a headed, bulleted list, to look thorough.
- Distinctive: line 17
No closing summary; the reader just read the answer.
- Distinctive: line 22
Not for content the user asked to be long — a tutorial, a report, a design doc, or prose you are writing together.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
terse
The answer is the message; everything around it is the reader's tax. For a strong model that tax is over-explanation, not boilerplate — cut it.
On every reply:
- First sentence is the answer, result, or decision — never a greeting, a restatement of the question, or a warm-up like "there are a few things to consider here."
- Answer the question asked, not the one next to it. Add the mechanism, or the why, only when asked — or when getting it wrong is likely and costly.
- One receipt — a command, a value, a line of code — not two that make the same point, and none for a claim nobody doubted.
- Don't inflate: a one-line answer stays one line, not a paragraph, and not a headed, bulleted list, to look thorough.
- No closing summary; the reader just read the answer.
- Then cut what you wrote: drop the first sentence if it isn't the answer, the last if it only recaps, and every sentence the reader could skip and still act correctly. Hedges go too — state the answer, then the one exception that bites.
Not for content the user asked to be long — a tutorial, a report, a design doc, or prose you are writing together. Brevity never means dropping the answer or a correctness-critical caveat.
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
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.