agentleFS
Sign inStart free
aomi-labsaomi-labs/docs/AGENTS.md

docs

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

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

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Use App (capitalized) not "app" when referring to the deployed unit.

    line 13
  2. Distinctive:

    Use non-custodial not "trustless" or "decentralized"

    line 14
  3. Distinctive:

    Use widget not "chat widget" on first reference, then "widget"

    line 15
  4. Very specific:

    Use headless library not "SDK" for @aomi-labs/react

    line 16
  5. Distinctive:

    Use simulate not "preview" or "dry-run"

    line 17
  6. Distinctive:

    Use active voice and second person ("you")

    line 21
  7. Distinctive:

    Keep sentences concise — one idea per sentence

    line 22
  8. Distinctive:

    Use sentence case for headings

    line 23
  9. Distinctive:

    Do not document internal infrastructure or deployment details

    line 30
  10. Distinctive:

    Do not document feature flags or experimental features

    line 31

≈ “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

Aomi Documentation

About this project

  • This is the Aomi documentation site built on Mintlify
  • Pages are MDX files with YAML frontmatter
  • Configuration lives in docs.json
  • Live at aomi.dev/docs

Terminology

  • Two-word system for the builder surface: a plugin is the thing a builder writes (the Rust cdylib the runtime loads dynamically — use for authoring, anatomy, SDK prose); an App is the thing they ship (the deployed, user-selectable unit — the word the CLI, aomi.toml, portal, and Developer Platform show). Define the bridge once per page at most; never rewrite commands, config keys, or UI labels to say "plugin"
  • Use App (capitalized) not "app" when referring to the deployed unit; not "agent" or "bot"
  • Use non-custodial not "trustless" or "decentralized"
  • Use widget not "chat widget" on first reference, then "widget"
  • Use headless library not "SDK" for @aomi-labs/react
  • Use simulate not "preview" or "dry-run"

Style preferences

  • Use active voice and second person ("you")
  • Keep sentences concise — one idea per sentence
  • Use sentence case for headings
  • Bold for UI elements: Click Settings
  • Code formatting for file names, commands, paths, and code references
  • Refer to the product as "Aomi" not "the Aomi platform" on subsequent mentions

Content boundaries

  • Do not document internal infrastructure or deployment details
  • Do not document feature flags or experimental features
  • Focus on what users and builders can do, not how the system works internally
  • Reference pages are for complete API/CLI/SDK reference; guides are for tutorials and walkthroughs

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 repositoryOne other file 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