agentleFS
Sign inStart free
drafaeldrafael/coding-harness/AGENTS.md

coding-harness

AGENTS.md1 starsChanged 6 months agoMITView on GitHub

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

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Use examples when explaining concepts

    line 5
  2. Distinctive:

    Ask clarifying questions when requirements are ambiguous

    line 6
  3. Distinctive:

    Prefer direct code and existing primitives over speculative abstractions.

    line 13
  4. Distinctive:

    Ask before adding frameworks, cross-cutting protocols, or substantial scope.

    line 14
  5. Distinctive:

    Keep security and reliability controls proportional to the real trust boundary.

    line 15
  6. Distinctive:

    Before finishing, audit the whole diff and remove dead experiments, unnecessary APIs, speculative limits, and one-consumer abstractions.

    line 18

≈ “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 Preferences

Communication Style

  • Be concise but thorough in explanations
  • Use examples when explaining concepts
  • Ask clarifying questions when requirements are ambiguous
  • Provide step-by-step instructions for complex tasks

Engineering Discipline

  • Make the smallest change that fixes the demonstrated problem; do not redesign adjacent systems without approval.
  • Base work on reproduced failures, explicit requirements, existing contracts, or credible current risks—not hypothetical concerns.
  • Prefer direct code and existing primitives over speculative abstractions. A new abstraction needs multiple current consumers.
  • Ask before adding frameworks, cross-cutting protocols, or substantial scope. Explain the simpler alternative and regression risk.
  • Keep security and reliability controls proportional to the real trust boundary; do not invent arbitrary limits or break valid behavior for theoretical threats.
  • Preserve known-good behavior. Revert failed approaches rather than layering fixes; after two unsuccessful attempts, stop and reassess the actual boundary.
  • Tests prove only the boundary they exercise. Report untested integration behavior as unverified.
  • Before finishing, audit the whole diff and remove dead experiments, unnecessary APIs, speculative limits, and one-consumer abstractions.

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