agentleFS
ahmed3elshaerahmed3elshaer/everything-claude-code-mobile/AGENTS.md

everything-claude-code-mobile

AGENTS.md65 starsChanged 5 months agoMITView on GitHub

Use this repository's mobile guidance for Android, iOS, and Kotlin Multiplatform work. Before implementation: Implementation rules: Useful workflows: Hosts without skills or subagents should treat this file as the compact fallback and read the relevant file under skills/ for detailed guidance.

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

6 rules. About 1 is common, 5 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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 this repository's mobile guidance for Android, iOS, and Kotlin Multiplatform work.

    line 3
  2. Distinctive:

    Prefer native platform APIs and already-installed dependencies.

    line 8
  3. Distinctive:

    Keep changes scoped to the requested feature.

    line 14
  4. Distinctive:

    Follow TDD for non-trivial behavior and run the platform's real build or test command.

    line 15
  5. Distinctive:

    Use structured concurrency: Kotlin coroutines and Swift async/await.

    line 16
  6. Common:

    Keep secrets out of source control and logs.

    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

Everything Claude Code Mobile

Use this repository's mobile guidance for Android, iOS, and Kotlin Multiplatform work.

Before implementation:

  1. Detect the project type from Gradle, Xcode, Swift Package, and KMP files.
  2. Prefer native platform APIs and already-installed dependencies.
  3. Load the relevant skill when the host supports Agent Skills.
  4. State architecture assumptions before making broad changes.

Implementation rules:

  • Keep changes scoped to the requested feature.
  • Follow TDD for non-trivial behavior and run the platform's real build or test command.
  • Use structured concurrency: Kotlin coroutines and Swift async/await.
  • Preserve null safety and avoid force unwraps unless an invariant is explicit.
  • Keep secrets out of source control and logs.
  • Respect accessibility, lifecycle, and offline behavior where applicable.

Useful workflows:

  • Feature delivery: feature-builder skill or /feature-build in Claude Code.
  • Android review: android-patterns, jetpack-compose, and mobile-testing.
  • iOS review: swift-patterns, swiftui-patterns, and ios-testing.
  • KMP review: expect-actual, shared-coroutines, and kmp-repositories.
  • Persistent context: use the mobile-memory, ios-memory, and kmp-context MCP tools when available.

Hosts without skills or subagents should treat this file as the compact fallback and read the relevant file under skills/ for detailed guidance.

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 repository5 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.

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.