agentleFS
kevin-leekevin-lee/ai-dumping-ground/AGENTS.md

ai-dumping-ground

AGENTS.md3 starsChanged 34 days agoMITView on GitHub

Instructions for AI agents that change this repository. Before you change one of these files, read docs/ai-output-folder-maintenance.md. It records the issues, the invariants, the decisions and the rejected options. A change made without them can break them again. Update the document in the same change when your change adds, renames or removes a script, changes an invariant or a decision, or removes a limit. When a new file uses the output folder, add it to the list above. Do not…

  • 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 repository8 other files it gives its agents.

The file

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

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before you change one of these files, read docs/ai-output-folder-maintenance.md.

    line 7
  2. Very specific:

    all files in skills/centralize-ai-output/

    line 11
  3. Distinctive:

    Update the document in the same change when your change adds, renames or removes a script, changes an invariant or a decision, or removes a …

    line 15
  4. Very specific:

    Do not put AGENTS.md, CLAUDE.md, GEMINI.md or other notes for maintainers in skills/<name>/.

    line 19

≈ “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

AGENTS

Instructions for AI agents that change this repository.

AI output folder

Before you change one of these files, read docs/ai-output-folder-maintenance.md. It records the issues, the invariants, the decisions and the rejected options. A change made without them can break them again.

  • ai-output-dir.sh, ai-output-choices.sh and migrate-ai-output.sh in skills/riper-5/scripts/, skills/pr-analysis/scripts/, skills/gen-motion-graphics/scripts/ and skills/centralize-ai-output/scripts/
  • video-output-choices.sh in skills/gen-motion-graphics/scripts/
  • all files in skills/centralize-ai-output/
  • the parts of skills/riper-5/SKILL.md, skills/pr-analysis/SKILL.md and skills/gen-motion-graphics/SKILL.md that choose the output folder
  • scripts/skills/test-ai-output-scripts.sh and scripts/skills/test-ai-output-scripts-linux.sh

Update the document in the same change when your change adds, renames or removes a script, changes an invariant or a decision, or removes a limit. When a new file uses the output folder, add it to the list above.

Skill folders

Do not put AGENTS.md, CLAUDE.md, GEMINI.md or other notes for maintainers in skills/<name>/. aiskills installs the whole skill folder, so the file goes to every user, and the paths in it do not exist there. Put them at the repository root or in docs/.

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.