agentleFS
Sign inStart free
umararshad4umararshad4/honey-stack/migrate/AGENTS.md

honey-stack / migrate

AGENTS.md4 starsChanged 15 days agoMITView on GitHub

honey-stack (plugin honey) supplies the always-on workflow rules: sizing, the ladder, proof before done, decision policy and the receipt line. Its skills are invoked as $grill, $plan, $execute, $debug, $tdd, $verify, $review, $ship; $honey lists the rest. This file holds only personal preferences.

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

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked to follow docs or specific instructions, don't assume anything: follow the script line by line.

    line 5
  2. Distinctive:

    Always use stable and latest tooling.

    line 6
  3. Distinctive:

    Write clean, scalable, easy-to-read code.

    line 10
  4. Very specific:

    Always use gh for GitHub reads and writes.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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

Personal instructions

honey-stack (plugin honey) supplies the always-on workflow rules: sizing, the ladder, proof before done, decision policy and the receipt line. Its skills are invoked as $grill, $plan, $execute, $debug, $tdd, $verify, $review, $ship; $honey lists the rest. This file holds only personal preferences.

  • When asked to follow docs or specific instructions, don't assume anything: follow the script line by line.
  • Always use stable and latest tooling.
  • Use the Exa plugin for deep web research when the task needs current information, comprehensive or multi-source research, technical/library research, GitHub or code discovery, papers, or company/competitor analysis, or when normal web search is insufficient. Verify important claims with multiple authoritative sources and cite them. Don't use Exa for simple, stable, self-contained questions.
  • In normal sessions don't run builds every time; only for a bigger change or when asked.
  • Be pragmatic and truthful: if an idea or request isn't good, say so and suggest better approaches; say so too when an approach is genuinely good.
  • Write clean, scalable, easy-to-read code.
  • Graphify: use selectively to visualize dependencies during unfamiliar-codebase work or complex refactors; don't run it by default.
  • /skill-doctor is a global skill; when invoked, follow its SKILL.md exactly.
  • Always use gh for GitHub reads and writes.

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