agentleFS
Sign inStart free
TheMarnixTheMarnix/agent-config-kit/profile/AGENTS.md

agent-config-kit / profile

AGENTS.md0 starsChanged 22 days agoMITView on GitHub

  • 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 31,774 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 repository4 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

8 rules. About 1 is common, 6 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Delete this comment when you are done.

    line 7
  2. Very specific:

    Use your own spelling, date format and time zone here (for example: British spelling, DD/MM/YYYY, Europe/London).

    line 13
  3. Distinctive:

    Ask only for missing access or decisions that are mine to make.

    line 20
  4. Distinctive:

    Never merge, deploy or change live systems without my explicit go-ahead.

    line 25
  5. Common:

    Never commit secrets. If auth blocks a push, report the exact blocker.

    line 26
  6. Distinctive:

    Run the project's tests and linter before saying work is done.

    line 31
  7. Distinctive:

    Prefer the simplest change that solves the problem.

    line 32
  8. Distinctive:

    When a task matches a skill's description, load that skill first.

    line 37

≈ “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.

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

Your global instructions

<!-- This file is read by every AI coding tool on your machine (Codex, Gemini, and Claude Code via the built CLAUDE.md). Replace everything below with your own preferences. Keep it short: every line is read at the start of every session. Delete this comment when you are done. -->

Communication

  • Lead with the outcome. Keep replies short and concrete.
  • Use your own spelling, date format and time zone here (for example: British spelling, DD/MM/YYYY, Europe/London).
  • Say what you verified and what you assumed.

Autonomy

  • Inspect and propose before making a change I have not approved.
  • Once I approve, finish the work including tests and repairs without stopping for routine permission.
  • Ask only for missing access or decisions that are mine to make.

Git

  • Work on a branch. Commit in small, reviewable steps.
  • Never merge, deploy or change live systems without my explicit go-ahead.
  • Never commit secrets. If auth blocks a push, report the exact blocker.

Code

  • Match the style of the surrounding code.
  • Run the project's tests and linter before saying work is done.
  • Prefer the simplest change that solves the problem.

Skills

  • Skills live in the skills/ folder of this repo and are linked into every tool by install.sh.
  • When a task matches a skill's description, load that skill first.

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.

Check your setup, free