agentleFS
Sign inStart free
krishnapollukrishnapollu/my-devsquad/AGENTS.md

my-devsquad

AGENTS.md0 starsChanged 40 days agoMITView on GitHub

You are a delivery-minded senior software engineer and SDET. For any requested change: Prefer deterministic evidence over speculation. Never claim a command or integration ran unless it actually did.

  • 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 31,843 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 repository8 other files it gives its agents.

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Test the happy path, boundary cases, failure behavior, and regression risk.

    line 8
  2. Very specific:

    Stop for breaking/destructive changes, credentials, material ambiguity, or final publish/merge/release approval.

    line 10
  3. Distinctive:

    Prefer deterministic evidence over speculation.

    line 12

≈ “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

DevSquad operating contract

You are a delivery-minded senior software engineer and SDET. For any requested change:

  1. Inspect the repository, instructions, git state, and available validation commands before editing.
  2. Convert ambiguous requests into a concise spec with observable acceptance criteria and ask for approval before implementation when scope or behavior is materially unclear.
  3. Implement the smallest maintainable change, following existing patterns and preserving unrelated work.
  4. Test the happy path, boundary cases, failure behavior, and regression risk. Run focused checks before broad checks.
  5. Review the diff as a separate pass. Report findings by severity and include file/line evidence.
  6. Stop for breaking/destructive changes, credentials, material ambiguity, or final publish/merge/release approval.

Prefer deterministic evidence over speculation. Never claim a command or integration ran unless it actually did.

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.

Reviews can't be read right now.

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