agentleFS
Sign inStart free
davidesilverdavidesilver/ZeroHuman-Agency/AGENTS.md

ZeroHuman-Agency

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed. Tradeoff: these guidelines bias toward caution over speed. For trivial tasks, use judgment. Don't assume. Don't hide confusion. Surface tradeoffs. Before implementing: - State your assumptions explicitly. If uncertain, ask. - If multiple interpretations exist, present them instead of picking silently. - If a simpler approach exists, say so. - Push back when warranted. - If something is unclear, stop, name what is confusing, and ask.

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

17 rules. About 0 are common, 17 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    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
  1. Distinctive:

    Don't assume. Don't hide confusion.

    line 9
  2. Distinctive:

    If multiple interpretations exist, present them instead of picking silently.

    line 13
  3. Distinctive:

    If a simpler approach exists, say so.

    line 14
  4. Distinctive:

    If something is unclear, stop, name what is confusing, and ask.

    line 16
  5. Distinctive:

    No features beyond what was asked.

    line 22
  6. Distinctive:

    No abstractions for single-use code.

    line 23
  7. Distinctive:

    No flexibility or configurability that was not requested.

    line 24
  8. Distinctive:

    No error handling for impossible scenarios.

    line 25
  9. Distinctive:

    If you write 200 lines and it could be 50, rewrite it.

    line 26
  10. Distinctive:

    Ask yourself: would a senior engineer say this is overcomplicated?

    line 28
  11. Distinctive:

    When editing existing code:

    line 34
  12. Distinctive:

    Don't improve adjacent code, comments, or formatting.

    line 35
  13. Distinctive:

    Don't refactor things that aren't broken.

    line 36
  14. Distinctive:

    If you notice unrelated dead code, mention it rather than deleting it.

    line 38
  15. Distinctive:

    When your changes create orphans:

    line 40
  16. Distinctive:

    Remove imports, variables, and functions that your changes made unused.

    line 41
  17. Distinctive:

    Don't remove pre-existing dead code unless asked.

    line 42

≈ “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

AGENTS.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: these guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them instead of picking silently.
  • If a simpler approach exists, say so.
  • Push back when warranted.
  • If something is unclear, stop, name what is confusing, and ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No flexibility or configurability that was not requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: would a senior engineer say this is overcomplicated? If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't improve adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you would do it differently.
  • If you notice unrelated dead code, mention it rather than deleting it.

When your changes create orphans:

  • Remove imports, variables, and functions that your changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" -> "Write tests for invalid inputs, then make them pass."
  • "Fix the bug" -> "Write a test that reproduces it, then make it pass."
  • "Refactor X" -> "Ensure tests pass before and after."

For multi-step tasks, state a brief plan:

1. [Step] -> verify: [check]
2. [Step] -> verify: [check]
3. [Step] -> verify: [check]

Strong success criteria let you loop independently. Weak criteria like "make it work" require constant clarification.

These guidelines are working if there are fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions happen before implementation rather than after mistakes.

Download now (ZIP)

  • 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 28,693 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.

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