everything-claude-code-mobile / rules
AGENTS.md65 starsChanged 5 months agoMITView on GitHub
Use /feature-build to orchestrate all agents through a 7-phase pipeline: Phases: Plan → Implement → Test → Build Fix → Quality Gate → Verify → Learn
We split this agents.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 5
Use /feature-build to orchestrate all agents through a 7-phase pipeline:
- Very specific: line 74
Use /feature-build for end-to-end feature construction
≈ “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.
Files
Agent Delegation
Build a Complete Feature
Use /feature-build to orchestrate all agents through a 7-phase pipeline:
/feature-build Add user authentication with biometricsPhases: Plan → Implement → Test → Build Fix → Quality Gate → Verify → Learn
When to Delegate
Code Review
| Situation | Agent |
| Android/Kotlin review | android-reviewer |
| iOS/Swift review | ios-reviewer |
| Security audit | mobile-security-reviewer |
| Performance review | mobile-performance-reviewer |
Build & Fix
| Situation | Agent |
| Gradle/AGP/R8 errors | android-build-resolver |
| Xcode/SPM/CocoaPods errors | xcode-build-resolver |
| Gradle optimization | gradle-expert |
Architecture & Planning
| Situation | Agent |
| Architecture decisions | mobile-architect |
| KMP shared module design | kmp-architect |
| Feature planning | feature-planner |
| Cross-platform models | shared-model-designer |
UI & Design
| Situation | Agent |
| Compose patterns | compose-guide |
| SwiftUI patterns | swiftui-guide |
| Material 3 Expressive | m3-expressive-guide |
| Apple Liquid Glass (iOS 26+) | liquid-glass-guide |
Implementation (Layer Agents)
| Situation | Agent |
| Domain models, use cases, DI | architecture-impl |
| API clients, DTOs, mappers | network-impl |
| Repositories, local DB, caching | data-impl |
| Screens, ViewModels, components | ui-impl |
| Navigation, DI wiring, integration | wiring-impl |
Testing
| Situation | Agent |
| TDD workflow (mandatory) | mobile-tdd-guide |
| E2E / instrumentation tests | mobile-e2e-runner |
| Unit tests (ViewModel, UseCase) | unit-test-writer |
| UI tests (Compose, SwiftUI) | ui-test-writer |
| Verification with pass@k | mobile-verifier |
Learning & Quality
| Situation | Agent |
| Extract codebase patterns | mobile-pattern-extractor |
| Context compaction | mobile-compactor |
Guidelines
- Delegate complex, specialized tasks
- Provide context and constraints
- Review agent output
- Use
/feature-buildfor end-to-end feature construction - Layer agents run in dependency order: architecture → network + UI → data → wiring
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.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- examples/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/everything-mobile.mdcCursor rule
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.

